---
schema_version: 7
rubric_version: "0.3"
canonical_url: "https://podium.do/compare/agents/products/ai-maestro/"
data_url: "https://podium.do/compare/agents/products/ai-maestro/data.json"
generated_at: 2026-11-22
oldest_checked_at: 2026-11-16
last_checked_at: 2026-11-16
publisher: "Podium"
---

# AI Maestro: ADE findings

> Podium publishes this catalog and sells an agent development environment. Podium chooses the products, criteria, sources and wording, so treat these pages as vendor-authored research. Check important claims against the linked primary sources. Sourced findings follow the same evidence rules for Podium and its competitors. Facts labeled Podium team research come from Podium's own team and have no linked source. None of this removes the conflict of interest.

> Based on data from adecomparison.com by Podium (https://adecomparison.com; source repository https://github.com/madeinorbit/ade-comparison, snapshot 4322f0c of 2026-11-22), used under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Source links and check dates are kept. Podium arranges the findings into pairs, applies its publication checks, and added its own research where marked "Podium team research". Data license terms: https://github.com/madeinorbit/ade-comparison/blob/4322f0c035f303791413639d1462a138443d8c1e/DATA-LICENSE.md

51 of 51 criteria have a sourced finding; 42 were also cross-checked by a second agent. Source checks: 2026-11-16. A missing sourced finding is not evidence that a capability is absent.

- Website: https://getaimaestro.com/
- Canonical HTML: https://podium.do/compare/agents/products/ai-maestro/
- Machine-readable JSON: https://podium.do/compare/agents/products/ai-maestro/data.json
- Rubric: https://podium.do/compare/agents/rubric/index.md
- Comparisons with AI Maestro on podium.do: 1 (listed in the JSON and HTML)
- Compare AI Maestro with any other product on adecomparison.com by Podium: https://adecomparison.com/compare/?products=ai-maestro

## Access and agent choice

### ACC-01: Client access

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Browser dashboard (desktop, tablet and phone layouts, installable as a PWA) served by the host, a launcher command, and a separate iPhone app; macOS and Linux hosts, Windows via WSL2; no desktop-native app or editor extension; Android app is an email-invited beta.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents), AI Maestro iPhone app and Android beta (closed source); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Windows only through WSL2.
- Mobile apps are closed source and Android is an invite-only beta.
- No editor extension.

- desktop_os — Desktop os [partial]: The server runs on macOS 12+ and Linux natively and on Windows only inside WSL2; it ships no native desktop app, only a Dock launcher that opens the dashboard. Sources: ai-maestro:readme, ai-maestro:reqs, ai-maestro:quickstart.
- mobile_apps — Mobile apps [partial]: An iPhone app is on the App Store (iOS 15.1+, 30 days free then $19.99 one-time per the vendor page); Android 7+ is an invite-only beta joined by emailing support. Neither app is in the public repositories. Sources: ai-maestro:iphonepage, ai-maestro:appstore, ai-maestro:srch-clients.
- browser — Browser [supported]: Full dashboard at http://localhost:23000 with chat, terminal, board, matrix, attention and team pages; installable as a PWA over https or localhost. Sources: ai-maestro:readme, ai-maestro:manifest.
- mobile_browser — Mobile browser [supported]: Responsive phone layouts (MobileDashboard, MobileChatView) and Add to Home Screen; the README shows phone Matrix, home and board screens. Sources: ai-maestro:readme, ai-maestro:product, ai-maestro:manifest.
- cli — Cli [supported]: The installer adds an ai-maestro command (open, start, stop, status) and the plugin ships aimaestro-agent.sh, aimaestro-task.sh and AMP scripts. Sources: ai-maestro:readme, ai-maestro:plugscripts.
- editor_extensions — Editor extensions [unsupported]: Bounded search finds no VS Code or JetBrains extension; the Claude Code mods are plugins for that CLI, not editor extensions. Sources: ai-maestro:srch-clients.
- task_actions — Task actions [partial]: Create agents, send chat, steer through the terminal, answer approval and question cards, move cards and schedule work from the dashboard; review of code changes and resume of an old session beyond waking the agent are not separate flows. Sources: ai-maestro:readme, ai-maestro:programs, ai-maestro:tasksdoc.
- notifications — Notifications [partial]: Push to the iPhone app through Expo (thin payload, 60 s cooldown); in-dashboard status, unread counts and Attention page; browser-level notifications are not documented. Sources: ai-maestro:pushexpo, ai-maestro:readme.
- cross_device_continuity — Cross device continuity [supported]: Agents live in tmux on the host and the dashboard is stateless in the browser, so any device on the network or Tailscale sees the same agents; mesh peers show all hosts. Sources: ai-maestro:concepts, ai-maestro:security.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:readme, ai-maestro:reqs, ai-maestro:quickstart, ai-maestro:iphonepage, ai-maestro:appstore, ai-maestro:srch-clients, ai-maestro:manifest, ai-maestro:product, ai-maestro:plugscripts, ai-maestro:programs, ai-maestro:tasksdoc, ai-maestro:pushexpo, ai-maestro:concepts, ai-maestro:security

### ACC-02: Agent and model choice

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Runs coding CLIs inside tmux: Claude Code, Codex CLI and Grok Build with chat, status and approval cards; Pi, Copilot CLI and OpenClaw with reduced support; any other terminal agent in the terminal tab. Also an embedded Claude Agent SDK chat path.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Support depth differs per CLI.
- No custom adapter interface; each reader is built into the server.

- harnesses — Harnesses [supported]: Claude Code, Codex CLI, Grok Build (first-class); Pi, GitHub Copilot CLI, OpenClaw recognised; Cursor, Gemini CLI, OpenCode and others only as terminal programs; Aider deprecated. Sources: ai-maestro:programs, ai-maestro:prognames.
- model_providers — Model providers [partial]: Model choice is left to each CLI; the product only passes a model setting (--model) for some and documents Claude Code on Vertex AI and Pi with Gemini on Vertex. Sources: ai-maestro:programs, ai-maestro:programlaunch.
- custom_adapters — Custom adapters [partial]: Any terminal program can be set as an agent program and typed into; transcript readers (transcript-codex/grok/pi/copilot.mjs) are built-in modules rather than a plugin API. Sources: ai-maestro:programs, ai-maestro:prognames.
- session_integration — Session integration [supported]: Default path controls the CLI through tmux (paste-buffer and key presses) plus hooks and transcript reading; the Streaming tab embeds the Claude Agent SDK with canUseTool approvals. Sources: ai-maestro:chatarch, ai-maestro:pkg, ai-maestro:hook.
- mixed_harness_operation — Mixed harness operation [supported]: One dashboard and mesh can host Claude Code, Codex and Grok Build agents side by side that message each other over AMP. Sources: ai-maestro:programs, ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:programs, ai-maestro:prognames, ai-maestro:programlaunch, ai-maestro:chatarch, ai-maestro:pkg, ai-maestro:hook, ai-maestro:readme

### ACC-03: Subscriptions, API keys and vendor credits

Verification status: Sourced (sourced)
Support: partial

Uses each CLI's own login or API key; AI Maestro holds no model credentials. Subscription use follows whatever the CLI supports; no vendor credits.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- No account switching in AI Maestro itself; each host uses the login its CLI holds.

- agent_subscriptions — Agent subscriptions [supported]: Agents run the user's logged-in CLI (Grok needs SuperGrok/X Premium+, Copilot needs a Copilot subscription, Claude Code its own login); the README says to bring your own agent subscriptions. Sources: ai-maestro:readme, ai-maestro:programs.
- api_accounts — Api accounts [supported]: CLIs started with their own API keys work; Claude Code on Vertex AI and Pi on Vertex are documented with helper scripts. Sources: ai-maestro:programs.
- vendor_credits — Vendor credits [unsupported]: No vendor credits, token sales or hosted tier exist ("no paid tier", "Is there a hosted version? Not yet"). Sources: ai-maestro:readme, ai-maestro:srch-billing.
- local_models — Local models [partial]: Pi can use a local OpenAI-compatible server and the repository tests used a fake local model, but local models are a property of the CLI, not an AI Maestro feature. Sources: ai-maestro:programs.
- account_switching — Account switching [unsupported]: Bounded search of lib, services, docs and README finds no multi-account switching; each host uses whichever login its CLI holds. Sources: ai-maestro:srch-acct.
- vendor_account_requirement — Vendor account requirement [supported]: No AI Maestro account or login is required ("No account, no telemetry"). Sources: ai-maestro:readme.
- provider_restrictions — Provider restrictions [partial]: Documents per-CLI login and subscription needs (Grok, Copilot) but no restrictions imposed by AI Maestro on third-party subscription use. Sources: ai-maestro:programs.

Checked 2026-11-16 (6 days old on 2026-11-22); not separately cross-checked.

Sources: ai-maestro:readme, ai-maestro:programs, ai-maestro:srch-billing, ai-maestro:srch-acct

### ACC-04: Onboarding and project prerequisites

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

One-line installer (curl | bash) for macOS, Linux or WSL2 needing Node 24, tmux and about 4 GB RAM to build; first agent via wizard, CLI or by starting a tmux session; local directory, local git and GitHub repos all work; BYO VPS and AWS paths documented.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Manual steps for installing each CLI and logging in on every host.

- first_task_setup — First task setup [supported]: Install, open localhost:23000, create an agent with the guided wizard, wake it and chat; or run aimaestro-agent.sh create; any existing tmux session is auto-discovered. Sources: ai-maestro:readme, ai-maestro:quickstart.
- no_git — No git [supported]: An agent is a working directory plus tmux session; git is not required to create or run one. Sources: ai-maestro:concepts.
- local_git_without_remote — Local git without remote [supported]: Repos are discovered by .git presence and read with git config; a remote origin is optional. Sources: ai-maestro:concepts.
- hosted_git — Hosted git [partial]: A GitHub token can be passed to Docker and EC2 agents for push; the host environment otherwise uses the user's existing git credentials. Sources: ai-maestro:docker, ai-maestro:tfreadme.
- prerequisite_guidance — Prerequisite guidance [supported]: README lists Node 24, tmux, RAM, WSL2 steps and Linux sizing; verify-installation.sh and the Doctor check readiness. Sources: ai-maestro:readme.
- managed_cloud_setup — Managed cloud setup [unsupported]: No vendor-managed cloud exists ("Is there a hosted / cloud version? Not yet"). Sources: ai-maestro:readme.
- byo_vps_onboarding — Byo vps onboarding [supported]: Documented Linux deployment guide, headless worker mode, remote-install.sh and the Terraform EC2 and ECS Fargate modules. Sources: ai-maestro:readme, ai-maestro:tfreadme, ai-maestro:cloud.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:readme, ai-maestro:quickstart, ai-maestro:concepts, ai-maestro:docker, ai-maestro:tfreadme, ai-maestro:cloud

### ACC-05: Programmable access

Verification status: Sourced (sourced)
Support: partial

Local REST API (no auth), WebSocket, shell scripts, signed webhooks and AMP API keys; no SDK; the product does not expose an MCP server for controlling the dashboard, only an MCP channel server for pushing messages into Claude Code.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Unauthenticated dashboard API by design.
- No SDK.

- cli — Cli [supported]: aimaestro-agent.sh (create, rename, hibernate, wake, delete), aimaestro-task.sh, amp-* scripts and the ai-maestro launcher. Sources: ai-maestro:plugscripts, ai-maestro:readme.
- api — Api [supported]: Next.js REST routes under app/api for agents, chat, messages, tasks, teams, hosts, schedules, webhooks and a versioned AMP API at /api/v1. Sources: ai-maestro:pkg, ai-maestro:tasksdoc.
- sdk — Sdk [unsupported]: No client SDK is published in the inspected repositories. Sources: ai-maestro:srch-clients.
- mcp_server — Mcp server [partial]: amp-channel-server.mjs is an MCP server that feeds inbox events into a running Claude Code session; no MCP server exposes agent control to other tools. Sources: ai-maestro:channel.
- webhooks — Webhooks [supported]: Webhook subscriptions with whsec_ signing secrets for agent and email events. Sources: ai-maestro:webhooks.
- operations — Operations [supported]: Create, inspect, chat/steer, hibernate, wake, delete, message and task operations exist in the API; stop is hibernate or tmux kill; code review is not an API operation. Sources: ai-maestro:tasksdoc, ai-maestro:programs.
- authentication — Authentication [partial]: The dashboard API has no authentication by design; AMP /api/v1 uses hashed API keys with rotation and cross-host AID/Ed25519 signatures. Sources: ai-maestro:security, ai-maestro:ampauth.
- stability — Stability [partial]: The dashboard API has no stability or deprecation policy in README, docs or SECURITY.md (bounded grep); the product is pre-1.0 (0.106.x) and only the AMP routes are namespaced /api/v1. Sources: ai-maestro:srch-stab, ai-maestro:pkg.

Checked 2026-11-16 (6 days old on 2026-11-22); not separately cross-checked.

Sources: ai-maestro:plugscripts, ai-maestro:readme, ai-maestro:pkg, ai-maestro:tasksdoc, ai-maestro:srch-clients, ai-maestro:channel, ai-maestro:webhooks, ai-maestro:programs, ai-maestro:security, ai-maestro:ampauth, ai-maestro:srch-stab

### ACC-06: External tools and extensions

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Agents are launched CLIs, so MCP and plugin support is inherited from them; AI Maestro adds a Claude Code plugin with 14 skills (Agent Skills standard), a plugin builder and a marketplace page, and an MCP channel server.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Mostly inherited from each CLI.

- mcp_client — Mcp client [partial]: MCP client features belong to the underlying CLI; AI Maestro only wires its own channel MCP server into Claude Code and offers Pi tool profiles that exclude mcp__* tools. Sources: ai-maestro:channel, ai-maestro:programs.
- plugins — Plugins [supported]: Claude Code plugin (marketplace ai-maestro-plugins, 14 skills), plugin builder with 150+ personalities, and Claude Code mods for inbox and secrets. Sources: ai-maestro:readme, ai-maestro:plugskills.
- custom_tools — Custom tools [partial]: Skills and scripts add tools for agents; Pi gets a copied extension (amp_*); no generic custom-tool registry for all programs. Sources: ai-maestro:plugskills, ai-maestro:programs.
- instructions_import — Instructions import [partial]: Team-level markdown instructions and per-agent files; CLAUDE.md and AGENTS.md handling is each CLI's; the installer writes a managed block into Pi AGENTS.md. Sources: ai-maestro:teamtype, ai-maestro:programs.
- authentication — Authentication [partial]: Integration credentials go through aim-secret (vault) or each tool's own login. Sources: ai-maestro:secrets.
- permission_scope — Permission scope [partial]: Per-program permission modes and a Pi messaging tool profile; skills have no separate scope model. Sources: ai-maestro:progchoices, ai-maestro:programs.
- integration_owner — Integration owner [supported]: Skills and scripts come from the AI Maestro plugin; MCP/tool wiring for other CLIs is owned by those CLIs; gateways are a separate repository. Sources: ai-maestro:plugskills, ai-maestro:gateways.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:channel, ai-maestro:programs, ai-maestro:readme, ai-maestro:plugskills, ai-maestro:teamtype, ai-maestro:secrets, ai-maestro:progchoices, ai-maestro:gateways

### ACC-07: Client implementation

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Web app: Next.js/React with xterm.js terminal and a Node server (tmux via node-pty) plus a PWA manifest; no Electron or Tauri client; the iPhone and Android apps are closed and their stack is not published (vendor page calls the chat "native").

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents), AI Maestro iPhone app and Android beta (closed source); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Mobile client implementation not public.

- desktop_implementation — Desktop implementation [supported]: No desktop client: the dashboard is a Next.js app with xterm.js/wterm terminals served by server.mjs; a Mac launcher only opens the browser. Sources: ai-maestro:pkg, ai-maestro:srch-clients.
- mobile_implementation — Mobile implementation [unknown]: The iPhone and Android apps are not in the public repositories; the App Store listing and the vendor page do not state the framework (push uses Expo, which suggests but does not prove React Native). Sources: ai-maestro:iphonepage, ai-maestro:appstore, ai-maestro:pushexpo.
- hybrids — Hybrids [supported]: Web UI plus PWA install; no hybrid wrapper in the repository. Sources: ai-maestro:manifest.
- implementation_evidence — Implementation evidence [partial]: Pinned package.json and source cover the web app; mobile builds are closed. Sources: ai-maestro:pkg, ai-maestro:appstore.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:pkg, ai-maestro:srch-clients, ai-maestro:iphonepage, ai-maestro:appstore, ai-maestro:pushexpo, ai-maestro:manifest

## Planning and context

### PLAN-01: Intake and external tracker relationship

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Local card creation on agent, team and project boards, prompt intake through chat, and import of an existing task list through a CLI; no GitHub/Linear/Jira issue import and no chat or Git triggers.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- external import: aimaestro-task.sh import accepts a JSON task list; no tracker connector found.
- chat git triggers: Slack/Discord/Email/WhatsApp gateways forward messages to agents; no Git or CI trigger found.
- sync: No external tracker sync exists in the inspected code.
- external roundtrips: Not applicable: nothing is synced to an external tracker.

- local_creation — Local creation [supported]: Cards are created from the dashboard, aimaestro-task.sh add/park and the REST API. Sources: ai-maestro:tasksdoc.
- prompt_intake — Prompt intake [supported]: Prompts go through chat or typed instructions; schedules can issue prompts. Sources: ai-maestro:chatarch, ai-maestro:sched.
- external_import — External import [partial]: aimaestro-task.sh import accepts a JSON task list; no tracker connector found. Sources: ai-maestro:tasksdoc, ai-maestro:srch-pr.
- chat_git_triggers — Chat git triggers [partial]: Slack/Discord/Email/WhatsApp gateways forward messages to agents; no Git or CI trigger found. Sources: ai-maestro:gateways, ai-maestro:srch-pr.
- authoritative_tracker — Authoritative tracker [supported]: The JSON board files in the user's ~/.aimaestro are authoritative; no external tracker is linked. Sources: ai-maestro:taskreg.
- stable_ids — Stable ids [supported]: Cards have UUIDs (short prefix shown in instructions). Sources: ai-maestro:taskreg.
- sync — Sync [unsupported]: No external tracker sync exists in the inspected code. Sources: ai-maestro:srch-pr.
- supported_edits — Supported edits [supported]: Edit subject, description, status, priority, assignee, owners, due, quadrant, waiting and blockers. Sources: ai-maestro:tasktype.
- external_roundtrips — External roundtrips [not-applicable]: Not applicable: nothing is synced to an external tracker. Sources: ai-maestro:srch-pr.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:tasksdoc, ai-maestro:chatarch, ai-maestro:sched, ai-maestro:srch-pr, ai-maestro:gateways, ai-maestro:taskreg, ai-maestro:tasktype

### PLAN-02: Durable task plans

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Cards carry description and a result field; a planning skill keeps persistent plan, findings and progress files; no per-task acceptance criteria or revision history.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- plans: The planning skill writes plan/findings/progress files for long tasks, and Claude plan mode is a permission mode; cards hold a description only.
- acceptance criteria: No acceptance-criteria field on cards in the inspected types.
- revisions: Cards store comments but no edit history.
- implementation links: Card origin links the agent, session, repo and thread that created it; commits trace back to sessions.

- plans — Plans [partial]: The planning skill writes plan/findings/progress files for long tasks, and Claude plan mode is a permission mode; cards hold a description only. Sources: ai-maestro:plugskills, ai-maestro:progchoices.
- acceptance_criteria — Acceptance criteria [unsupported]: No acceptance-criteria field on cards in the inspected types. Sources: ai-maestro:tasktype.
- editors — Editors [supported]: Card detail and board edit description and fields in the dashboard. Sources: ai-maestro:tasksdoc.
- revisions — Revisions [unsupported]: Cards store comments but no edit history. Sources: ai-maestro:tasktype.
- implementation_links — Implementation links [partial]: Card origin links the agent, session, repo and thread that created it; commits trace back to sessions. Sources: ai-maestro:tasksdoc, ai-maestro:commitrace.
- amendment — Amendment [supported]: A card can be edited while its agent works; instructions can be resent. Sources: ai-maestro:tasksvc.
- restart_persistence — Restart persistence [supported]: Boards are JSON files on disk that survive server restarts. Sources: ai-maestro:taskreg.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:plugskills, ai-maestro:progchoices, ai-maestro:tasktype, ai-maestro:tasksdoc, ai-maestro:commitrace, ai-maestro:tasksvc, ai-maestro:taskreg

### PLAN-03: Hierarchy, dependencies and evolving scope

Verification status: Sourced (sourced)
Support: partial

Flat cards with status, blockedBy dependencies (cycle-checked, readiness derived), kinds and quadrants; teams and projects group cards; no epics or arbitrary parent/child hierarchy and no dependency-gated dispatch.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- epics: No epic or parent field on cards; teams and projects are containers.
- hierarchy: Card hierarchy is not modelled; agents have a manager hierarchy and org chart instead.
- readiness: isBlocked is computed from incomplete blockers and completing a card reports newly unblocked cards; there is no ready queue.
- enforcement: Blockers are shown, not enforced: no code stops an agent from starting a blocked card.

- epics — Epics [unsupported]: No epic or parent field on cards; teams and projects are containers. Sources: ai-maestro:tasktype, ai-maestro:teamtype.
- hierarchy — Hierarchy [unsupported]: Card hierarchy is not modelled; agents have a manager hierarchy and org chart instead. Sources: ai-maestro:tasktype, ai-maestro:agenttype.
- blockers — Blockers [supported]: blockedBy lists of card IDs with a derived blocks list and isBlocked flag. Sources: ai-maestro:taskreg.
- readiness — Readiness [partial]: isBlocked is computed from incomplete blockers and completing a card reports newly unblocked cards; there is no ready queue. Sources: ai-maestro:taskreg.
- enforcement — Enforcement [unsupported]: Blockers are shown, not enforced: no code stops an agent from starting a blocked card. Sources: ai-maestro:taskreg, ai-maestro:tasksvc.
- state_propagation — State propagation [partial]: Completion returns the unblocked cards but does not move them. Sources: ai-maestro:taskreg.
- task_to_epic — Task to epic [unsupported]: No epic concept to grow into. Sources: ai-maestro:tasktype.
- identity_retention — Identity retention [not-applicable]: Not applicable: cards cannot grow into epics; a card keeps its UUID, comments and history across edits. Sources: ai-maestro:taskreg, ai-maestro:tasktype.
- workflow_constraints — Workflow constraints [supported]: No rigid workflow is required; any status can be set. Sources: ai-maestro:tasktype.

Checked 2026-11-16 (6 days old on 2026-11-22); not separately cross-checked.

Sources: ai-maestro:tasktype, ai-maestro:teamtype, ai-maestro:agenttype, ai-maestro:taskreg, ai-maestro:tasksvc

### PLAN-04: Shared context and memory

Verification status: Sourced (sourced)
Support: partial

Per-agent working directory with CLI instructions, team-level markdown instructions, 14 skills, a skill marketplace and per-agent opt-in long-term memory (memory cards and entity graph with recall) plus code graph and generated docs.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Memory is opt-in per agent and team memory is not shared by default.

- instructions — Instructions [supported]: Team instructions field and each CLI's own instruction files; managed AGENTS.md block for Pi. Sources: ai-maestro:teamtype, ai-maestro:programs.
- skills — Skills [supported]: 14 skills in the Agent Skills format installed with the plugin plus a marketplace service. Sources: ai-maestro:plugskills, ai-maestro:readme.
- project_docs — Project docs [supported]: Docs skill and DocumentationPanel index generated documentation of the agent codebase. Sources: ai-maestro:readme.
- memory — Memory [supported]: Nightly consolidation of conversations into memory cards and an entity graph, with recall injected on prompts, per agent opt-in. Sources: ai-maestro:ltm.
- scope — Scope [supported]: Memory and code graph are indexed per agent and what it owns; team memory is not shared by default. Sources: ai-maestro:readme, ai-maestro:ltm.
- provenance — Provenance [supported]: Each memory statement is backed by the passages it came from. Sources: ai-maestro:readme, ai-maestro:ltm.
- correction — Correction [supported]: A PATCH route edits a memory's content, category and context, and memories are rebuilt from sources by nightly consolidation. Sources: ai-maestro:memroute, ai-maestro:ltm.
- deletion — Deletion [supported]: A DELETE route removes one memory by id and MemoryViewer has a per-memory delete button. Sources: ai-maestro:memroute, ai-maestro:memviewer.
- freshness — Freshness [supported]: Ended relations are marked and recurrence weights knowledge; nightly consolidation keeps it current. Sources: ai-maestro:readme, ai-maestro:ltm.
- takeover_continuity — Takeover continuity [supported]: Memory and agent identity survive new sessions and agent transfer between hosts. Sources: ai-maestro:readme, ai-maestro:concepts.

Checked 2026-11-16 (6 days old on 2026-11-22); not separately cross-checked.

Sources: ai-maestro:teamtype, ai-maestro:programs, ai-maestro:plugskills, ai-maestro:readme, ai-maestro:ltm, ai-maestro:memsvc, ai-maestro:concepts, ai-maestro:memroute, ai-maestro:memviewer

### PLAN-05: Architecture and API awareness

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Code graph (CozoDB, ts-morph, delta indexing), generated docs search, memory search and conversation search per agent; images through each CLI; no cross-repo knowledge connectors or review-time enforcement.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- external knowledge: Plugin personalities and gateways; no connector to external knowledge bases in core.
- multimodal inputs: Agent uploads and AMP attachments exist; image reasoning depends on the CLI.
- citations: Memory cards cite passages; graph answers list callers and dependencies.
- conflict detection: No conflict-detection logic found.

- code_search — Code search [supported]: graph-query and docs-search skills plus AgentSearch tab. Sources: ai-maestro:readme, ai-maestro:plugskills.
- indexing — Indexing [supported]: Delta indexing of the codebase graph and transcripts (index-delta route). Sources: ai-maestro:readme.
- external_knowledge — External knowledge [partial]: Plugin personalities and gateways; no connector to external knowledge bases in core. Sources: ai-maestro:readme, ai-maestro:gateways.
- multimodal_inputs — Multimodal inputs [partial]: Agent uploads and AMP attachments exist; image reasoning depends on the CLI. Sources: ai-maestro:srch-review.
- freshness — Freshness [supported]: Delta index updates and nightly memory runs. Sources: ai-maestro:readme, ai-maestro:ltm.
- access_scope — Access scope [supported]: Per-agent indexes keyed to the agent working directory. Sources: ai-maestro:readme.
- api_retrieval — Api retrieval [supported]: REST routes for graph, docs, memory and search per agent. Sources: ai-maestro:readme.
- citations — Citations [partial]: Memory cards cite passages; graph answers list callers and dependencies. Sources: ai-maestro:ltm.
- conflict_detection — Conflict detection [unsupported]: No conflict-detection logic found. Sources: ai-maestro:srch-review.
- review_enforcement — Review enforcement [unsupported]: No review-time architectural enforcement. Sources: ai-maestro:srch-review.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:readme, ai-maestro:plugskills, ai-maestro:gateways, ai-maestro:srch-review, ai-maestro:ltm

### PLAN-06: Native issue management and idea backlog

Verification status: Sourced (sourced)
Support: partial

Native cards with create, edit, comments, priority, quadrant, assignee, owners, due, kinds (idea/bug/research/task), Eisenhower Matrix, Attention page and Kanban; no labels, archive or search listed; ideas can be parked without starting work.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- label: kind and org labels exist; no free-form labels.
- search: the Matrix filters by agent name only; no free-text card search was found.
- archive: Cards are completed or deleted; no archive state.
- project epic views: Agent, team and project boards and an Org view; no epics.

- create — Create [supported]: Create from dashboard, CLI and API. Sources: ai-maestro:tasksdoc.
- edit — Edit [supported]: Edit all card fields. Sources: ai-maestro:tasktype.
- discuss — Discuss [supported]: Comments with operator or agent authors. Sources: ai-maestro:tasktype.
- prioritize — Prioritize [supported]: priority and urgent/important quadrant. Sources: ai-maestro:tasktype.
- label — Label [partial]: kind and org labels exist; no free-form labels. Sources: ai-maestro:tasktype.
- assign — Assign [supported]: Primary assignee plus up to 10 owners; project cards forward instructions to the assignee. Sources: ai-maestro:tasksdoc, ai-maestro:tasksvc.
- search — Search [partial]: The Matrix page filters cards by agent name or alias; no free-text search over card subjects or descriptions exists in the inspected components. Sources: ai-maestro:matrixpage.
- filter — Filter [supported]: Matrix, Org and Attention views filter by quadrant, org, overdue and waiting. Sources: ai-maestro:tasksdoc.
- archive — Archive [unsupported]: Cards are completed or deleted; no archive state. Sources: ai-maestro:tasktype.
- reopen — Reopen [supported]: Status can be moved back from completed. Sources: ai-maestro:tasktype.
- project_epic_views — Project epic views [partial]: Agent, team and project boards and an Org view; no epics. Sources: ai-maestro:tasksdoc.
- idea_parking — Idea parking [supported]: `aimaestro-task.sh park` saves an idea card (kind idea) off the board. Sources: ai-maestro:tasksdoc.
- explicit_dispatch — Explicit dispatch [partial]: Assignment forwards a typed instruction to the assignee on project boards; own-board cards need the agent to read them. Sources: ai-maestro:tasksvc.
- task_session_separation — Task session separation [partial]: Cards are separate from sessions and carry origin ids, but a card does not own sessions. Sources: ai-maestro:tasksdoc.
- metadata — Metadata [supported]: Status, due, owners, origin, kind, quadrant, waiting, result, blockers, comments. Sources: ai-maestro:tasktype.
- durable_states — Durable states [supported]: backlog, pending, in_progress, review, waiting, completed persisted with timestamps. Sources: ai-maestro:tasktype, ai-maestro:taskreg.
- external_tracker_requirement — External tracker requirement [supported]: No external tracker is needed. Sources: ai-maestro:taskreg.

Checked 2026-11-16 (6 days old on 2026-11-22); not separately cross-checked.

Sources: ai-maestro:tasksdoc, ai-maestro:tasktype, ai-maestro:tasksvc, ai-maestro:taskreg, ai-maestro:matrixpage

### PLAN-07: Agent-native issue operations

Verification status: Sourced (sourced)
Support: partial

Agents operate the same cards through aimaestro-task.sh and the REST API (add, list, due, owners, park, import, show, delete own board) with operator/agent attribution on comments; permissions are by board scope, not roles.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- claim: An agent can add a card to its own board or take owner status; no explicit claim lock.
- children: No child cards.
- attribution: Comments record operator or agent author; card field edits are not attributed.
- permissions: Agents can only delete cards on their own board; no per-user permissions.
- conflicts: JSON file read-modify-write with no lock or version check.

- shared_ids — Shared ids [supported]: Humans and agents use the same UUID cards. Sources: ai-maestro:tasksdoc, ai-maestro:taskreg.
- read — Read [supported]: list and show. Sources: ai-maestro:tasksdoc.
- create — Create [supported]: add and park. Sources: ai-maestro:tasksdoc.
- update — Update [supported]: due, owners and PATCH updates. Sources: ai-maestro:tasksdoc.
- claim — Claim [partial]: An agent can add a card to its own board or take owner status; no explicit claim lock. Sources: ai-maestro:tasksdoc.
- assign — Assign [supported]: assigneeAgentId and owners. Sources: ai-maestro:tasksvc.
- state_changes — State changes [supported]: Status updates via API. Sources: ai-maestro:tasktype.
- dependencies — Dependencies [supported]: blockedBy settable through the API. Sources: ai-maestro:taskreg.
- children — Children [unsupported]: No child cards. Sources: ai-maestro:tasktype.
- results — Results [supported]: A result field on cards. Sources: ai-maestro:tasktype.
- human_visibility — Human visibility [supported]: Boards, Matrix and Attention read the same files. Sources: ai-maestro:tasksdoc.
- attribution — Attribution [partial]: Comments record operator or agent author; card field edits are not attributed. Sources: ai-maestro:tasktype.
- permissions — Permissions [partial]: Agents can only delete cards on their own board; no per-user permissions. Sources: ai-maestro:tasksdoc, ai-maestro:product.
- conflicts — Conflicts [unsupported]: task-registry reads and rewrites the whole JSON board synchronously with no lock, version check or merge, so the last writer wins. Sources: ai-maestro:srch-taskcas.

Checked 2026-11-16 (6 days old on 2026-11-22); not separately cross-checked.

Sources: ai-maestro:tasksdoc, ai-maestro:taskreg, ai-maestro:tasksvc, ai-maestro:tasktype, ai-maestro:product, ai-maestro:srch-taskcas

### PLAN-08: Living product specifications

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

No living product specification: persistent docs, memory and planning files exist but without revisions, approvals or drift checks.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- persistent requirements: No requirements store separate from cards, memory and docs.
- human edits: Not applicable beyond editing files.
- agent edits: Planning skill files are agent-written but not a spec system.
- revisions: No spec revisions.

- persistent_requirements — Persistent requirements [unsupported]: No requirements store separate from cards, memory and docs. Sources: ai-maestro:tasktype, ai-maestro:ltm.
- human_edits — Human edits [unsupported]: Not applicable beyond editing files. Sources: ai-maestro:tasktype.
- agent_edits — Agent edits [unsupported]: Planning skill files are agent-written but not a spec system. Sources: ai-maestro:plugskills.
- revisions — Revisions [unsupported]: No spec revisions. Sources: ai-maestro:tasktype.
- approvals — Approvals [unsupported]: No spec approval flow. Sources: ai-maestro:tasktype.
- implementation_links — Implementation links [unsupported]: No requirement links. Sources: ai-maestro:tasktype.
- later_retrieval — Later retrieval [partial]: Memory recall and docs search retrieve earlier knowledge in later tasks. Sources: ai-maestro:ltm.
- drift_detection — Drift detection [unsupported]: No drift detection. Sources: ai-maestro:srch-review.
- review_integration — Review integration [unsupported]: No review integration. Sources: ai-maestro:srch-review.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:tasktype, ai-maestro:ltm, ai-maestro:plugskills, ai-maestro:srch-review

## Coordination and automation

### COORD-01: Parallel work

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Any number of agents run concurrently, each in its own tmux session (or container/instance), across hosts; the sidebar and Zoom wall show working, needs-you, ready and offline states; no documented quota.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- quotas: No agent-count quota found; AMP rate limit is 60 messages per minute.
- observed concurrency: Vendor reports 80+ agents and a Linux memory sizing doc; this catalog did not run it.

- concurrent_sessions — Concurrent sessions [supported]: Each agent is a tmux session; 80+ agents are described across hosts. Sources: ai-maestro:readme, ai-maestro:concepts.
- concurrent_tasks — Concurrent tasks [supported]: Each agent works on its own task concurrently. Sources: ai-maestro:readme.
- quotas — Quotas [unsupported]: No agent-count quota found; AMP rate limit is 60 messages per minute. Sources: ai-maestro:ampsvc, ai-maestro:srch-budget.
- observed_concurrency — Observed concurrency [partial]: Vendor reports 80+ agents and a Linux memory sizing doc; this catalog did not run it. Sources: ai-maestro:readme.
- status_visibility — Status visibility [supported]: Working, Needs you, Ready, offline and hibernated states, unread counts and Attention page. Sources: ai-maestro:readme, ai-maestro:programs.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:readme, ai-maestro:concepts, ai-maestro:ampsvc, ai-maestro:srch-budget, ai-maestro:programs

### COORD-02: Ownership and dispatch

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Assignment of cards to agents and co-owners; agents own repositories by convention; no queue, routing engine or enforced exclusive ownership; diagnostics warn about shared folders.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- claims: Owners list marks shared responsibility; no exclusive claim.
- queues: wake-queue and message queues exist for waking agents, not for work.
- routing: Closed teams route external messages through the chief-of-staff.
- duplicate prevention: Diagnostics warn when two agents share a folder; agents clone separately.

- human_assignment — Human assignment [supported]: Humans assign cards to agents and set a human manager in agent metadata. Sources: ai-maestro:tasksvc, ai-maestro:agenttype.
- agent_assignment — Agent assignment [supported]: Agents add and assign cards via CLI/API. Sources: ai-maestro:tasksdoc.
- claims — Claims [partial]: Owners list marks shared responsibility; no exclusive claim. Sources: ai-maestro:tasksdoc.
- queues — Queues [partial]: wake-queue and message queues exist for waking agents, not for work. Sources: ai-maestro:tasksvc.
- routing — Routing [partial]: Closed teams route external messages through the chief-of-staff. Sources: ai-maestro:teamtype.
- duplicate_prevention — Duplicate prevention [partial]: Diagnostics warn when two agents share a folder; agents clone separately. Sources: ai-maestro:diag, ai-maestro:concepts.
- ownership_enforcement — Ownership enforcement [unsupported]: Ownership is a convention; nothing prevents two agents from taking the same card. Sources: ai-maestro:taskreg.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:tasksvc, ai-maestro:agenttype, ai-maestro:tasksdoc, ai-maestro:teamtype, ai-maestro:diag, ai-maestro:concepts, ai-maestro:taskreg

### COORD-03: Inspectable delegation and communication

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Agents message each other with signed AMP messages (inbox, reply, wake), teams run split-pane meetings, agents have manager/chief-of-staff roles, and a skill lets an agent create and manage other agents; no parent/child spawn with returned results.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- model harness effort: Model and program are set per agent at creation or wake; no per-delegation effort control.
- results return: Replies come back as AMP messages; there is no structured result return.
- live progress: Status and chat of any agent are visible; no parent-level child progress view.

- roles — Roles [supported]: AgentRole manager, chief-of-staff, member, plus a manager link and org chart. Sources: ai-maestro:agenttype.
- model_harness_effort — Model harness effort [partial]: Model and program are set per agent at creation or wake; no per-delegation effort control. Sources: ai-maestro:progchoices.
- messages — Messages [supported]: AMP signed messages with priority and types, delivered by Stop hook, channel or typing. Sources: ai-maestro:hook, ai-maestro:channel.
- results_return — Results return [partial]: Replies come back as AMP messages; there is no structured result return. Sources: ai-maestro:hook.
- cross_harness — Cross harness [supported]: Claude Code, Codex and Grok agents exchange AMP messages. Sources: ai-maestro:programs.
- orchestration_owner — Orchestration owner [supported]: Product-owned messaging and agent management skills; no hidden provider subagents. Sources: ai-maestro:plugskills.
- activation — Activation [supported]: Installed with the plugin; messaging on by default. Sources: ai-maestro:readme.
- authentication — Authentication [supported]: AMP API keys and Ed25519 signatures; AID identity. Sources: ai-maestro:ampauth.
- live_progress — Live progress [partial]: Status and chat of any agent are visible; no parent-level child progress view. Sources: ai-maestro:readme.
- retained_results — Retained results [supported]: Messages persist in the inbox files and transcripts. Sources: ai-maestro:ampauth.
- followup — Followup [supported]: Any agent can be messaged again after finishing. Sources: ai-maestro:readme.
- invocation — Invocation [supported]: Natural language ("send a message to backend") through the agent-messaging skill. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:agenttype, ai-maestro:progchoices, ai-maestro:hook, ai-maestro:channel, ai-maestro:programs, ai-maestro:plugskills, ai-maestro:readme, ai-maestro:ampauth

### COORD-04: Unattended triggers

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Per-agent cron schedules stored with the agent and fired by the dashboard server when the agent is idle; schedules travel with the agent; overlap skipped; no event triggers other than gateways and webhooks.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- events: Gateway messages and AMP messages wake agents; no repository event triggers.
- completion conditions: No completion conditions on schedules.
- retries: Error back-off instead of immediate retry; MAX 50 executions logged.

- schedules — Schedules [supported]: Cron expressions with timezone per schedule. Sources: ai-maestro:schedreg.
- events — Events [partial]: Gateway messages and AMP messages wake agents; no repository event triggers. Sources: ai-maestro:gateways, ai-maestro:hook.
- recurring_tasks — Recurring tasks [supported]: Morning triage, nightly checks and weekly reports are the documented use. Sources: ai-maestro:readme.
- completion_conditions — Completion conditions [unsupported]: No completion conditions on schedules. Sources: ai-maestro:sched.
- scheduler_location — Scheduler location [supported]: Runs inside the AI Maestro server on the host (60 s loop). Sources: ai-maestro:sched.
- overlaps — Overlaps [supported]: A run in flight is skipped. Sources: ai-maestro:agentsched.
- retries — Retries [partial]: Error back-off instead of immediate retry; MAX 50 executions logged. Sources: ai-maestro:agentsched, ai-maestro:schedreg.
- client_independence — Client independence [supported]: Runs server-side; closing the browser does not stop it, but the host must run. Sources: ai-maestro:sched.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:schedreg, ai-maestro:gateways, ai-maestro:hook, ai-maestro:readme, ai-maestro:sched, ai-maestro:agentsched

### COORD-05: Intervention and attention

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Chat and terminal steering, hibernate/wake, approval and question cards, Attention page and phone push; stop is hibernation or terminating the session; terminal and chat share the same tmux session.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- pause: Hibernate stops the session; no mid-turn pause.
- notifications: Push to the iPhone app and in-dashboard Needs you; Slack/Discord gateways.
- escalation: Agent-to-human managers and the chief-of-staff role; no timed escalation.
- visible errors: Delivery verification and Doctor checks; some failures only show in the terminal.

- pause — Pause [partial]: Hibernate stops the session; no mid-turn pause. Sources: ai-maestro:readme.
- stop — Stop [supported]: Hibernate or delete agent; terminal Ctrl+C. Sources: ai-maestro:readme.
- resume — Resume [supported]: Wake resumes the agent (claude --continue style) with history. Sources: ai-maestro:readme.
- steer — Steer [supported]: Chat or terminal at any time. Sources: ai-maestro:chatarch.
- notifications — Notifications [partial]: Push to the iPhone app and in-dashboard Needs you; Slack/Discord gateways. Sources: ai-maestro:pushexpo, ai-maestro:gateways.
- pending_decisions — Pending decisions [supported]: Questions and approvals appear as cards; Attention page lists them. Sources: ai-maestro:programs.
- escalation — Escalation [partial]: Agent-to-human managers and the chief-of-staff role; no timed escalation. Sources: ai-maestro:agenttype.
- visible_errors — Visible errors [partial]: Delivery verification and Doctor checks; some failures only show in the terminal. Sources: ai-maestro:chatarch.
- chat_terminal_parity — Chat terminal parity [partial]: The tmux chat path reads the terminal as text and is documented as inherently below 100% reliable. Sources: ai-maestro:chatarch.
- retained_history — Retained history [supported]: Transcripts, search, export and playback tabs. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:readme, ai-maestro:chatarch, ai-maestro:pushexpo, ai-maestro:gateways, ai-maestro:programs, ai-maestro:agenttype

### COORD-06: Fleet and epic management UI

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Dashboard, Zoom wall, Matrix, Attention, Org and Teams pages show agents and cards across hosts with status colours, due and overdue badges; no failed/reviewing lanes or epic dependency graph.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- parent child: Manager hierarchy and org view; no parent/child cards.
- dependencies: blockedBy on cards; no dependency graph.
- history: Playback and card timestamps; no fleet activity timeline.
- workload: Matrix counts open cards per agent and host.

- fleet_fixture — Fleet fixture [supported]: Vendor screenshots use a demo company (Northwind Labs) with scripted agents; this catalog did not run a fixture. Sources: ai-maestro:readme.
- parent_child — Parent child [partial]: Manager hierarchy and org view; no parent/child cards. Sources: ai-maestro:agenttype, ai-maestro:tasksdoc.
- dependencies — Dependencies [partial]: blockedBy on cards; no dependency graph. Sources: ai-maestro:taskreg.
- attention — Attention [supported]: Attention page: overdue, waiting on you and agents needing you. Sources: ai-maestro:tasksdoc.
- history — History [partial]: Playback and card timestamps; no fleet activity timeline. Sources: ai-maestro:readme.
- workload — Workload [partial]: Matrix counts open cards per agent and host. Sources: ai-maestro:tasksdoc.
- navigation_errors — Navigation errors [unknown]: Failed-run navigation is not documented. Sources: ai-maestro:tasksdoc.
- fixture_mode — Fixture mode [unknown]: Catalog did not exercise the product. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:readme, ai-maestro:agenttype, ai-maestro:tasksdoc, ai-maestro:taskreg

### COORD-07: Workflow flexibility and orchestration visibility

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

No mandatory preset; natural-language messaging and teams; per-agent program, model and permission mode set at creation; war-room meetings show participating agents; no coordinator-run plan views.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- growing epic: No epics.
- presets: Wake dialog launch choices and plugin personalities act as presets; none required.
- in run changes: Chat steering and card edits; no coordinator re-plan.
- live roles: Team meeting tiles show agents; roles are manager/COS/member.

- quick_task — Quick task [supported]: Chat with an agent or create a card. Sources: ai-maestro:chatarch.
- growing_epic — Growing epic [unsupported]: No epics. Sources: ai-maestro:tasktype.
- presets — Presets [partial]: Wake dialog launch choices and plugin personalities act as presets; none required. Sources: ai-maestro:progchoices.
- natural_language — Natural language [supported]: Agents are told what to do in plain language, including messaging. Sources: ai-maestro:readme.
- agent_configuration — Agent configuration [supported]: Program, model, permission mode, tools profile, avatar and role per agent. Sources: ai-maestro:progchoices.
- in_run_changes — In run changes [partial]: Chat steering and card edits; no coordinator re-plan. Sources: ai-maestro:chatarch.
- live_roles — Live roles [partial]: Team meeting tiles show agents; roles are manager/COS/member. Sources: ai-maestro:teamtype.
- retained_relationships — Retained relationships [partial]: Manager links and card origin persist. Sources: ai-maestro:agenttype.
- discoverability — Discoverability [supported]: Help panel, tutorials and docs. Sources: ai-maestro:readme.
- auth_friction — Auth friction [partial]: Each CLI must be logged in on every host. Sources: ai-maestro:programs.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:chatarch, ai-maestro:tasktype, ai-maestro:progchoices, ai-maestro:readme, ai-maestro:teamtype, ai-maestro:agenttype, ai-maestro:programs

## Execution and reliability

### RUN-01: Laptop-independent execution

Verification status: Sourced (sourced)
Support: partial

Agents run in tmux on your host, on mesh peers you own (including headless workers), in Docker, or on EC2/ECS Fargate in your own AWS account; no vendor cloud. tmux sessions keep running when the browser closes; the host must stay on.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- managed cloud: No vendor-operated cloud ("Not yet").
- resources: Docker agents default to 2 CPUs and 4g; Linux sizing guide for hosts.
- expiry: EC2/ECS run until destroyed; Docker restart unless-stopped; no vendor lifetime.

- local — Local [supported]: tmux on the host running the dashboard. Sources: ai-maestro:readme.
- byo_remote — Byo remote [supported]: Peer hosts over Tailscale or LAN, headless workers, EC2 and Fargate via Terraform. Sources: ai-maestro:readme, ai-maestro:concepts, ai-maestro:cloud.
- self_hosted — Self hosted [supported]: The whole product is self-hosted; each host runs its own server. Sources: ai-maestro:readme.
- managed_cloud — Managed cloud [unsupported]: No vendor-operated cloud ("Not yet"). Sources: ai-maestro:readme.
- hybrid — Hybrid [supported]: Mixed local, Docker and cloud agents appear in one dashboard. Sources: ai-maestro:readme.
- provisioning — Provisioning [supported]: Terraform modules provision EC2 and ECS from the dashboard or CLI. Sources: ai-maestro:cloud, ai-maestro:tfreadme.
- payer — Payer [supported]: The user pays their cloud provider and CLI subscriptions. Sources: ai-maestro:readme.
- resources — Resources [partial]: Docker agents default to 2 CPUs and 4g; Linux sizing guide for hosts. Sources: ai-maestro:docker, ai-maestro:readme.
- region — Region [supported]: The user picks the AWS region through the aws_region Terraform variable (default us-east-1); there is no vendor region because there is no vendor cloud. Sources: ai-maestro:tfvars.
- expiry — Expiry [partial]: EC2/ECS run until destroyed; Docker restart unless-stopped; no vendor lifetime. Sources: ai-maestro:docker.
- client_disconnect — Client disconnect [supported]: tmux sessions persist after the dashboard or browser closes. Sources: ai-maestro:security.
- other_device_continuation — Other device continuation [supported]: Any browser or the iPhone app can reach the same host. Sources: ai-maestro:concepts, ai-maestro:iphonepage.

Checked 2026-11-16 (6 days old on 2026-11-22); not separately cross-checked.

Sources: ai-maestro:readme, ai-maestro:concepts, ai-maestro:cloud, ai-maestro:tfreadme, ai-maestro:docker, ai-maestro:security, ai-maestro:iphonepage, ai-maestro:tfvars

### RUN-02: Workspace and process isolation

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Default tmux agents run as the host user in their own working directory (separate clone), not worktrees; Docker agents get a hardened container with CPU and memory limits; EC2 gives a dedicated instance. No documented network or secret boundary for tmux agents.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=local, docker, cloud; region=not specified; harness=not specified.

Limitations:
- branch: Agents integrate through git branches by convention; no product branch management.
- worktree: The product deliberately does not use worktrees to isolate agents (README); agents may use them inside their clone.
- vm: EC2 agents run on dedicated instances through Terraform; no local VM isolation.
- os sandbox: Only launch flags of supported CLIs (e.g. Codex sandbox mode); tmux agents are unsandboxed.

- checkout — Checkout [supported]: Each agent owns its working directory and clones what it owns. Sources: ai-maestro:concepts, ai-maestro:diag.
- branch — Branch [partial]: Agents integrate through git branches by convention; no product branch management. Sources: ai-maestro:readme.
- worktree — Worktree [unsupported]: The product deliberately does not use worktrees to isolate agents (README); agents may use them inside their clone. Sources: ai-maestro:readme, ai-maestro:diag.
- container — Container [supported]: Docker agent runtime with --cap-drop=ALL, no-new-privileges, noexec tmpfs, --cpus and --memory. Sources: ai-maestro:docker.
- vm — Vm [partial]: EC2 agents run on dedicated instances through Terraform; no local VM isolation. Sources: ai-maestro:cloud, ai-maestro:tfreadme.
- os_sandbox — Os sandbox [partial]: Only launch flags of supported CLIs (e.g. Codex sandbox mode); tmux agents are unsandboxed. Sources: ai-maestro:progchoices, ai-maestro:srch-sandbox.
- filesystem — Filesystem [partial]: Container mounts /workspace plus listed mounts; tmux agents see the user home. Sources: ai-maestro:docker, ai-maestro:security.
- process — Process [partial]: Container PID namespace per agent; tmux agents share the user. Sources: ai-maestro:docker, ai-maestro:security.
- network — Network [unsupported]: Docker publishes a port and adds host.docker.internal; no network policy. Sources: ai-maestro:docker.
- secrets — Secrets [partial]: aim-secret hides values from model context; file backend readable by the agent. Sources: ai-maestro:secrets.
- code_separation — Code separation [partial]: Separate clones per agent; shared folders produce a warning. Sources: ai-maestro:diag.
- security_boundary — Security boundary [partial]: SECURITY.md and Pi docs state tools restrictions are not a security boundary. Sources: ai-maestro:security, ai-maestro:programs.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:concepts, ai-maestro:diag, ai-maestro:readme, ai-maestro:docker, ai-maestro:cloud, ai-maestro:tfreadme, ai-maestro:progchoices, ai-maestro:srch-sandbox, ai-maestro:security, ai-maestro:secrets, ai-maestro:programs

### RUN-03: Recovery, expiry and continuity

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

tmux persists sessions across dashboard restarts; wake resumes the CLI; transcripts reload for chat; agents can be transferred between hosts; context loss and manual repair for stuck panes are documented.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- worker crash: Hibernate/wake and Doctor checks; crashed CLIs need a wake.
- expiry: Claude Code deletes transcripts after 30 days; AI Maestro rebuilds history from its message index for memory.
- state reconstruction: Pending reconcile and chat-state files; Doctor.
- context loss: Compaction and the 30-day transcript limit are cited.

- client_disconnect — Client disconnect [supported]: tmux sessions persist after closing the dashboard. Sources: ai-maestro:security.
- worker_crash — Worker crash [partial]: Hibernate/wake and Doctor checks; crashed CLIs need a wake. Sources: ai-maestro:readme.
- service_restart — Service restart [supported]: Agents are tmux sessions independent of the Node server and are rediscovered. Sources: ai-maestro:concepts.
- expiry — Expiry [partial]: Claude Code deletes transcripts after 30 days; AI Maestro rebuilds history from its message index for memory. Sources: ai-maestro:ltm.
- transcript_reload — Transcript reload [supported]: Chat history reads each CLI transcript files. Sources: ai-maestro:programs.
- process_reconnect — Process reconnect [supported]: Terminal re-attaches to tmux. Sources: ai-maestro:concepts.
- task_resume — Task resume [supported]: Wake continues the agent session. Sources: ai-maestro:programs.
- state_reconstruction — State reconstruction [partial]: Pending reconcile and chat-state files; Doctor. Sources: ai-maestro:hook.
- context_loss — Context loss [partial]: Compaction and the 30-day transcript limit are cited. Sources: ai-maestro:ltm.
- duplicate_actions — Duplicate actions [partial]: Stop-hook dedup of delivered messages; duplicate typing risks are discussed. Sources: ai-maestro:hook, ai-maestro:chatarch.
- manual_repair — Manual repair [partial]: Troubleshooting docs and the Doctor. Sources: ai-maestro:readme.
- multi_day_continuity — Multi day continuity [supported]: Long-term memory and persistent identity target months-long continuity. Sources: ai-maestro:ltm.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:security, ai-maestro:readme, ai-maestro:concepts, ai-maestro:ltm, ai-maestro:programs, ai-maestro:hook, ai-maestro:chatarch

### RUN-04: Development environment reliability

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Per-host installer and scripts for CLIs, Node and tmux; no snapshot or service orchestration; separate clones per agent; no automatic port allocation between workspaces beyond Docker port assignment.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- dependencies: install.sh sets up the dashboard; each CLI and its dependencies are installed by the user (install-pi.sh, install-claude-vertex.sh).
- caches: No cache sharing between agents.
- snapshots: No snapshots; agent export/import archives exist.
- services: No service orchestration for project dependencies.

- dependencies — Dependencies [partial]: install.sh sets up the dashboard; each CLI and its dependencies are installed by the user (install-pi.sh, install-claude-vertex.sh). Sources: ai-maestro:readme, ai-maestro:programs.
- caches — Caches [unsupported]: No cache sharing between agents. Sources: ai-maestro:srch-sandbox.
- snapshots — Snapshots [unsupported]: No snapshots; agent export/import archives exist. Sources: ai-maestro:srch-sandbox.
- services — Services [unsupported]: No service orchestration for project dependencies. Sources: ai-maestro:srch-sandbox.
- ports — Ports [partial]: Docker agents are assigned a host port; tmux agents manage their own. Sources: ai-maestro:docker.
- secrets — Secrets [supported]: aim-secret injects named secrets into commands. Sources: ai-maestro:secrets.
- duplicate_installs — Duplicate installs [partial]: Each clone has its own installs; the README recommends partial clones for large repos. Sources: ai-maestro:readme.
- collisions — Collisions [partial]: Not handled for tmux agents. Sources: ai-maestro:docker.
- remote_setup — Remote setup [supported]: remote-install.sh and headless mode. Sources: ai-maestro:readme.
- automatic_repair — Automatic repair [partial]: Installers repair partially; the Doctor diagnoses. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:readme, ai-maestro:programs, ai-maestro:srch-sandbox, ai-maestro:docker, ai-maestro:secrets

### RUN-05: Limits and failure handling

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

No time, turn, token or spend limits; AMP is rate limited and Docker agents have CPU/memory caps; tmux and hook timeouts only.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- time limits: No run time limits.
- turn limits: No turn limits.
- token limits: No token limits.
- spend limits: No spend limits; the cost doc explains cache effects only.

- time_limits — Time limits [unsupported]: No run time limits. Sources: ai-maestro:srch-budget.
- turn_limits — Turn limits [unsupported]: No turn limits. Sources: ai-maestro:srch-budget.
- token_limits — Token limits [unsupported]: No token limits. Sources: ai-maestro:srch-budget.
- spend_limits — Spend limits [unsupported]: No spend limits; the cost doc explains cache effects only. Sources: ai-maestro:srch-budget, ai-maestro:costscript.
- timeouts — Timeouts [partial]: Hook (5 s) and delivery timeouts; no task timeout. Sources: ai-maestro:hook.
- retries — Retries [partial]: Message delivery retries and scheduler back-off. Sources: ai-maestro:agentsched.
- provider_failures — Provider failures [partial]: Error text is shown in chat history for Pi/Copilot logs; no provider failover. Sources: ai-maestro:programs.
- enforcement — Enforcement [partial]: Docker CPU and memory are enforced; the rest are not limits. Sources: ai-maestro:docker, ai-maestro:ampsvc.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:srch-budget, ai-maestro:costscript, ai-maestro:hook, ai-maestro:agentsched, ai-maestro:programs, ai-maestro:docker, ai-maestro:ampsvc

### RUN-06: Truthful status and operational statistics

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Per-agent tiles for sessions, tokens and estimated cost (Claude Code OTLP opt-in), working/idle/needs-you status from hooks and transcripts, Doctor diagnostics and conversation search/playback; no failure reasons or fleet statistics export.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- logs: Chat transcripts, terminal and server logs; log rotation script.
- traces: No tracing.
- failure reasons: Errors appear in chat for readers that parse them; Doctor.
- usage export: Transcript export; no usage export.

- logs — Logs [partial]: Chat transcripts, terminal and server logs; log rotation script. Sources: ai-maestro:programs.
- traces — Traces [unsupported]: No tracing. Sources: ai-maestro:srch-budget.
- failure_reasons — Failure reasons [partial]: Errors appear in chat for readers that parse them; Doctor. Sources: ai-maestro:programs.
- usage_export — Usage export [partial]: Transcript export; no usage export. Sources: ai-maestro:readme.
- task_stats — Task stats [unsupported]: No per-card statistics. Sources: ai-maestro:tasktype.
- agent_stats — Agent stats [supported]: Sessions, tokens and estimated cost tiles per agent. Sources: ai-maestro:agenttype, ai-maestro:telsvc.
- project_stats — Project stats [unsupported]: No project statistics. Sources: ai-maestro:tasktype.
- time_stats — Time stats [partial]: Timestamps on cards; metrics tiles lack time series. Sources: ai-maestro:taskreg.
- failure_status — Failure status [partial]: Needs-you and offline states; no explicit failed state. Sources: ai-maestro:programs.
- approval_status — Approval status [supported]: Needs-you status and approval cards. Sources: ai-maestro:programs.
- reconnect_consistency — Reconnect consistency [partial]: Hooks and pane parsing reconcile state; a stale "working" file is not trusted after 10 minutes. Sources: ai-maestro:programs.
- performance_method — Performance method [unsupported]: No benchmark method; ADEMark does not list this product. Sources: ai-maestro:readme.
- responsiveness — Responsiveness [unknown]: Not measured by this catalog. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:programs, ai-maestro:srch-budget, ai-maestro:readme, ai-maestro:tasktype, ai-maestro:agenttype, ai-maestro:telsvc, ai-maestro:taskreg

### RUN-07: Per-task API and compute cost

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Claude Code agents can show tokens and an estimated cost tile when OTLP telemetry is turned on; a script breaks down a session transcript by cache share; no per-task, epic or subscription-aware cost.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- task cost: No per-card cost.
- session cost: Per-agent (Claude session) estimated cost when telemetry is enabled.
- child cost: No child cost.
- epic cost: No epics.

- task_cost — Task cost [unsupported]: No per-card cost. Sources: ai-maestro:tasktype.
- session_cost — Session cost [partial]: Per-agent (Claude session) estimated cost when telemetry is enabled. Sources: ai-maestro:telemetry, ai-maestro:telsvc.
- child_cost — Child cost [unsupported]: No child cost. Sources: ai-maestro:telsvc.
- epic_cost — Epic cost [unsupported]: No epics. Sources: ai-maestro:tasktype.
- harness_aggregation — Harness aggregation [unsupported]: Cost telemetry covers Claude programs only. Sources: ai-maestro:telemetry.
- billed_vs_estimated — Billed vs estimated [partial]: Tile is an estimate; the script reports proportions, not dollars. Sources: ai-maestro:costscript.
- tokens — Tokens [supported]: totalTokensUsed metric. Sources: ai-maestro:telsvc.
- subscription_allowance — Subscription allowance [unsupported]: No subscription allowance view. Sources: ai-maestro:costscript.
- provider_reconciliation — Provider reconciliation [unsupported]: No reconciliation. Sources: ai-maestro:costscript.
- compute_cost — Compute cost [unsupported]: No compute cost. Sources: ai-maestro:srch-billing.
- refresh_delay — Refresh delay [partial]: Exports every 30 s when enabled. Sources: ai-maestro:telemetry.
- alerts — Alerts [unsupported]: No budget alerts. Sources: ai-maestro:srch-budget.
- export — Export [unsupported]: No cost export. Sources: ai-maestro:srch-budget.
- drilldown — Drilldown [unsupported]: No drill-down. Sources: ai-maestro:telsvc.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:tasktype, ai-maestro:telemetry, ai-maestro:telsvc, ai-maestro:costscript, ai-maestro:srch-billing, ai-maestro:srch-budget

### RUN-08: Compute-aware scheduling and verification

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Docker CPU/memory limits per agent and a 60 s scheduler; host load hints and a bounded embedding process; no queues, backpressure or check deduplication for agent work.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- concurrency: Memory indexing bounded; scheduler skips overlapping runs; no global concurrency cap.
- queues: Wake queue only.
- backpressure: No backpressure.
- host awareness: Host load hints (host-load.ts) and Linux sizing guide.

- concurrency — Concurrency [partial]: Memory indexing bounded; scheduler skips overlapping runs; no global concurrency cap. Sources: ai-maestro:agentsched, ai-maestro:readme.
- queues — Queues [partial]: Wake queue only. Sources: ai-maestro:tasksvc.
- cpu_ram — Cpu ram [supported]: Docker --cpus and --memory per agent. Sources: ai-maestro:docker.
- backpressure — Backpressure [unsupported]: No backpressure. Sources: ai-maestro:srch-budget.
- host_awareness — Host awareness [partial]: Host load hints (host-load.ts) and Linux sizing guide. Sources: ai-maestro:readme.
- check_reuse — Check reuse [unsupported]: No check reuse. Sources: ai-maestro:srch-review.
- check_deduplication — Check deduplication [unsupported]: No check deduplication. Sources: ai-maestro:srch-review.
- bounded_tests — Bounded tests [unsupported]: No test runner. Sources: ai-maestro:srch-review.
- cancellation — Cancellation [partial]: Hibernate and kill session. Sources: ai-maestro:readme.
- fairness — Fairness [unsupported]: No fairness logic. Sources: ai-maestro:srch-budget.
- recovery — Recovery [partial]: tmux persistence. Sources: ai-maestro:security.
- shared_limits — Shared limits [unsupported]: No shared limits. Sources: ai-maestro:srch-budget.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:agentsched, ai-maestro:readme, ai-maestro:tasksvc, ai-maestro:docker, ai-maestro:srch-budget, ai-maestro:srch-review, ai-maestro:security

## Human collaboration and control

### TEAM-01: Live human collaboration

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Not designed for several humans on one fleet ("no attribution or handoff model exists"); multiple browsers can open the same agent, agents have a people directory and calls, and cards support co-owner agents; no presence or co-prompting rules.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- visibility: Any device on the network sees the same dashboard, but there are no user accounts.
- discussion: Card comments with operator/agent authors; operator is not identified individually.
- presence: Agent presence only; no human presence.
- coprompting: Several browsers can send to one agent; no ordering rules.

- visibility — Visibility [partial]: Any device on the network sees the same dashboard, but there are no user accounts. Sources: ai-maestro:product, ai-maestro:security.
- discussion — Discussion [partial]: Card comments with operator/agent authors; operator is not identified individually. Sources: ai-maestro:tasktype.
- comments — Comments [supported]: Card comments exist. Sources: ai-maestro:tasktype.
- presence — Presence [partial]: Agent presence only; no human presence. Sources: ai-maestro:agenttype.
- coprompting — Coprompting [partial]: Several browsers can send to one agent; no ordering rules. Sources: ai-maestro:product.
- ordering — Ordering [unsupported]: No input ordering. Sources: ai-maestro:product.
- conflicts — Conflicts [unsupported]: No conflict handling. Sources: ai-maestro:product.
- attribution — Attribution [unsupported]: No human attribution (PRODUCT.md). Sources: ai-maestro:product.
- permissions — Permissions [unsupported]: No permissions. Sources: ai-maestro:security, ai-maestro:srch-sso.
- plan_restrictions — Plan restrictions [not-applicable]: Free MIT; no plans. Sources: ai-maestro:readme.
- owner_online — Owner online [supported]: The host owner must keep the host running; no owner presence is required. Sources: ai-maestro:security.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:product, ai-maestro:security, ai-maestro:tasktype, ai-maestro:agenttype, ai-maestro:srch-sso, ai-maestro:readme

### TEAM-02: Roles and access boundaries

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

No organization/project/task roles, membership, SSO or provisioning; only agent messaging roles and a People directory.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- organization roles: No human roles.
- project roles: No project roles.
- task roles: No task roles.
- membership: A People directory and agent managers exist but are not memberships with permissions.

- organization_roles — Organization roles [unsupported]: No human roles. Sources: ai-maestro:srch-sso.
- project_roles — Project roles [unsupported]: No project roles. Sources: ai-maestro:srch-sso.
- task_roles — Task roles [unsupported]: No task roles. Sources: ai-maestro:srch-sso.
- membership — Membership [partial]: A People directory and agent managers exist but are not memberships with permissions. Sources: ai-maestro:agenttype.
- sso — Sso [unsupported]: No SSO. Sources: ai-maestro:srch-sso.
- provisioning — Provisioning [unsupported]: No SCIM or provisioning. Sources: ai-maestro:srch-sso.
- unauthorized_access — Unauthorized access [unsupported]: No application authentication; network perimeter only. Sources: ai-maestro:security.
- revocation — Revocation [partial]: AMP API keys can be revoked and rotated; no user revocation. Sources: ai-maestro:ampauth.
- plan_scope — Plan scope [not-applicable]: No plans. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:srch-sso, ai-maestro:agenttype, ai-maestro:security, ai-maestro:ampauth, ai-maestro:readme

### TEAM-03: Approvals and temporary access

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Approvals for the CLIs' own prompts appear as chat cards (Claude from hook and pane; Codex, Grok, Copilot from pane); permission modes per CLI; secrets requests and SQL write requests need a person; full autonomy is selectable; tmux agents are not sandboxed.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- network: No network approval layer.
- delivery: agentic-sql write requests require person approval; no merge/delivery gate.
- approver identity: No approver identity.
- lifetime: Each CLI's own scopes.

- command — Command [supported]: Command approval cards in chat for Claude Code, Codex, Grok and Copilot. Sources: ai-maestro:programs.
- tool — Tool [supported]: Tool and edit approval cards. Sources: ai-maestro:programs.
- network — Network [unsupported]: No network approval layer. Sources: ai-maestro:srch-sandbox.
- secret — Secret [supported]: A secret request card with a masked field. Sources: ai-maestro:secrets, ai-maestro:readme.
- delivery — Delivery [partial]: agentic-sql write requests require person approval; no merge/delivery gate. Sources: ai-maestro:plugskills.
- approver_identity — Approver identity [unsupported]: No approver identity. Sources: ai-maestro:product.
- lifetime — Lifetime [partial]: Each CLI's own scopes. Sources: ai-maestro:programs.
- allow — Allow [supported]: Clicking an option sends the same key. Sources: ai-maestro:programs.
- deny — Deny [supported]: Same card options include deny. Sources: ai-maestro:programs.
- revoke — Revoke [unsupported]: No revoke surface beyond CLI. Sources: ai-maestro:programs.
- tunnels — Tunnels [not-applicable]: No tunnels. Sources: ai-maestro:readme.
- defaults — Defaults [partial]: Default supervised; fullAutonomy available (e.g. --always-approve). Sources: ai-maestro:progchoices.
- safer_modes — Safer modes [supported]: planOnly, trustEdits, smartAuto modes and Pi messaging profile. Sources: ai-maestro:progchoices, ai-maestro:programs.
- enforcement — Enforcement [partial]: Enforced by each CLI, not by AI Maestro; Pi docs say tool restriction is not a boundary. Sources: ai-maestro:programs.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:programs, ai-maestro:srch-sandbox, ai-maestro:secrets, ai-maestro:readme, ai-maestro:plugskills, ai-maestro:product, ai-maestro:progchoices

### TEAM-04: Decision and activity history

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Messages, transcripts, card comments and playback persist locally; an audit trail is only a draft spec; history is files the agent user can edit.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- actions: Transcripts and commit-to-session trace; no action log.
- approvals: Approval clicks are not logged (audit trail unbuilt).
- edits: Git history; no card edit history.
- decisions: No decision records.

- actions — Actions [partial]: Transcripts and commit-to-session trace; no action log. Sources: ai-maestro:commitrace, ai-maestro:auditspec.
- approvals — Approvals [unsupported]: Approval clicks are not logged (audit trail unbuilt). Sources: ai-maestro:auditspec.
- edits — Edits [partial]: Git history; no card edit history. Sources: ai-maestro:tasktype.
- discussion — Discussion [supported]: AMP messages and card comments. Sources: ai-maestro:tasktype.
- decisions — Decisions [unsupported]: No decision records. Sources: ai-maestro:auditspec.
- cross_user_persistence — Cross user persistence [unsupported]: No users. Sources: ai-maestro:product.
- cross_session_persistence — Cross session persistence [supported]: Messages and memory persist across sessions. Sources: ai-maestro:ltm.
- export — Export [supported]: Transcript export and agent export. Sources: ai-maestro:readme.
- mutability — Mutability [partial]: Spec states agents run as the same OS user and can edit audit files. Sources: ai-maestro:auditspec.
- retention — Retention [partial]: Claude transcripts 30 days; AI Maestro message index keeps more. Sources: ai-maestro:ltm.
- integrity — Integrity [unsupported]: Hash chain is planned only. Sources: ai-maestro:auditspec.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:commitrace, ai-maestro:auditspec, ai-maestro:tasktype, ai-maestro:product, ai-maestro:ltm, ai-maestro:readme

### TEAM-05: Review experience and guidance

Verification status: Sourced (sourced)
Support: partial

No review workflow: no diff viewer, request-changes flow or shipping guidance; chat cards, attention page and mobile layouts help triage; review is done in the terminal or Git host.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- pending reviews: Cards in review status appear on the Attention page.
- change understanding: No diff UI.
- evidence navigation: Commit-to-session trace.
- comments: Card comments only.

- pending_reviews — Pending reviews [partial]: Cards in review status appear on the Attention page. Sources: ai-maestro:tasksdoc.
- change_understanding — Change understanding [unsupported]: No diff UI. Sources: ai-maestro:srch-review.
- evidence_navigation — Evidence navigation [partial]: Commit-to-session trace. Sources: ai-maestro:commitrace.
- comments — Comments [partial]: Card comments only. Sources: ai-maestro:tasktype.
- request_changes — Request changes [unsupported]: No request-changes flow. Sources: ai-maestro:srch-review.
- shipping_guidance — Shipping guidance [unsupported]: None. Sources: ai-maestro:srch-pr.
- effort — Effort [unknown]: Not measured. Sources: ai-maestro:readme.
- missed_evidence — Missed evidence [unknown]: Not measured. Sources: ai-maestro:readme.
- keyboard — Keyboard [partial]: Documented shortcuts cover terminal scrolling and copy/paste only, plus search and playback keys in code; no documented keyboard flow for review or approval. Sources: ai-maestro:qs-keys.
- narrow_screen — Narrow screen [supported]: Mobile layouts exist. Sources: ai-maestro:product, ai-maestro:readme.
- context_switching — Context switching [partial]: One-click agent switching is a stated design goal. Sources: ai-maestro:product.
- roles — Roles [partial]: Roles per agent. Sources: ai-maestro:agenttype.
- retained_context — Retained context [partial]: Transcripts persist. Sources: ai-maestro:programs.

Checked 2026-11-16 (6 days old on 2026-11-22); not separately cross-checked.

Sources: ai-maestro:tasksdoc, ai-maestro:srch-review, ai-maestro:commitrace, ai-maestro:tasktype, ai-maestro:srch-pr, ai-maestro:readme, ai-maestro:product, ai-maestro:agenttype, ai-maestro:programs, ai-maestro:qs-keys

### TEAM-06: Colleague takeover and continuity

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

A different person can open the same dashboard and agent chat, and agents can be transferred between hosts with their repositories; there is no attribution or handoff model.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- ongoing takeover: Any browser can drive an agent; transfer moves it to another host.
- same task: Cards visible to all.
- decisions: No decision log.
- artifacts: Files and canvas pages stay with the agent.

- ongoing_takeover — Ongoing takeover [partial]: Any browser can drive an agent; transfer moves it to another host. Sources: ai-maestro:product, ai-maestro:concepts.
- same_task — Same task [partial]: Cards visible to all. Sources: ai-maestro:tasksdoc.
- session_history — Session history [supported]: Transcripts and playback. Sources: ai-maestro:programs.
- decisions — Decisions [unsupported]: No decision log. Sources: ai-maestro:auditspec.
- artifacts — Artifacts [partial]: Files and canvas pages stay with the agent. Sources: ai-maestro:readme.
- permissions — Permissions [unsupported]: No permissions. Sources: ai-maestro:security.
- runtime_context — Runtime context [supported]: tmux session keeps the live runtime. Sources: ai-maestro:concepts.
- owner_disconnect — Owner disconnect [supported]: The host keeps running. Sources: ai-maestro:security.
- ownership — Ownership [unsupported]: No ownership transfer for humans. Sources: ai-maestro:product.
- attribution — Attribution [unsupported]: No attribution. Sources: ai-maestro:product.
- context_loss — Context loss [partial]: Memory and transcripts retained; terminal scrollback may be lost. Sources: ai-maestro:ltm.
- harness_transfer — Harness transfer [partial]: Agents can be re-woken with a different program; history readers differ. Sources: ai-maestro:programs.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:product, ai-maestro:concepts, ai-maestro:tasksdoc, ai-maestro:programs, ai-maestro:auditspec, ai-maestro:readme, ai-maestro:security, ai-maestro:ltm

## Verification and delivery

### SHIP-01: Retained artifacts and outputs

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas pages drawn by agents, chat history, uploads, AMP attachments and shared files (AFP) persist; no diff, screenshot or recording gallery and no test/reviewer outputs.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- diffs: No diff artifact.
- screenshots: Attachments can carry images; no gallery.
- recordings: No recordings.
- previews: Canvas pages render in the dashboard.

- diffs — Diffs [unsupported]: No diff artifact. Sources: ai-maestro:srch-review.
- documents — Documents [supported]: Generated docs and canvas pages. Sources: ai-maestro:readme.
- screenshots — Screenshots [partial]: Attachments can carry images; no gallery. Sources: ai-maestro:readme.
- recordings — Recordings [unsupported]: No recordings. Sources: ai-maestro:srch-review.
- previews — Previews [partial]: Canvas pages render in the dashboard. Sources: ai-maestro:readme.
- test_outputs — Test outputs [unsupported]: No test output store. Sources: ai-maestro:srch-review.
- reviewer_outputs — Reviewer outputs [unsupported]: No reviewer concept. Sources: ai-maestro:srch-review.
- gallery — Gallery [unsupported]: No artifact gallery. Sources: ai-maestro:srch-review.
- task_links — Task links [partial]: Card origin links back to agent/session. Sources: ai-maestro:tasksdoc.
- revision_links — Revision links [partial]: Commit-to-session lookup. Sources: ai-maestro:commitrace.
- persistence — Persistence [supported]: Files persist on disk and in S3-compatible AFP. Sources: ai-maestro:readme.
- child_findings — Child findings [unsupported]: No child reviewer. Sources: ai-maestro:srch-review.
- prompt_leakage — Prompt leakage [unknown]: Not examined. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:srch-review, ai-maestro:readme, ai-maestro:tasksdoc, ai-maestro:commitrace

### SHIP-02: Verification and spec gates

Verification status: Agent cross-checked (agent-cross-checked)
Support: unsupported

No verification gates: tests, lint, CI and review are whatever the agent runs; no required checks or spec checks.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

- tests — Tests [unsupported]: No test runner in product flows. Sources: ai-maestro:srch-review.
- lint — Lint [unsupported]: None. Sources: ai-maestro:srch-review.
- types — Types [unsupported]: None. Sources: ai-maestro:srch-review.
- ci — Ci [unsupported]: No CI integration found. Sources: ai-maestro:srch-pr.
- independent_review — Independent review [unsupported]: None. Sources: ai-maestro:srch-review.
- spec_checks — Spec checks [unsupported]: None. Sources: ai-maestro:srch-review.
- required_checks — Required checks [unsupported]: None. Sources: ai-maestro:srch-review.
- failure_blocking — Failure blocking [unsupported]: Nothing blocks delivery. Sources: ai-maestro:srch-pr.
- requirement_conflicts — Requirement conflicts [unsupported]: None. Sources: ai-maestro:srch-review.
- configured_policy — Configured policy [unsupported]: None. Sources: ai-maestro:srch-review.
- enforced_policy — Enforced policy [unsupported]: None. Sources: ai-maestro:srch-review.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:srch-review, ai-maestro:srch-pr

### SHIP-03: Git and pull request workflow

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Agents run git themselves in their own clones; the product reads repos and traces commits to sessions; Docker/EC2 agents receive a GitHub token; no PR creation or CI response flow.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- branches: Per-agent clone with own branch by convention.
- worktrees: Not used by the product.
- commits: Commits traced to sessions.
- pull requests: No PR code found.

- branches — Branches [partial]: Per-agent clone with own branch by convention. Sources: ai-maestro:readme.
- worktrees — Worktrees [unsupported]: Not used by the product. Sources: ai-maestro:readme, ai-maestro:diag.
- commits — Commits [partial]: Commits traced to sessions. Sources: ai-maestro:commitrace.
- pull_requests — Pull requests [unsupported]: No PR code found. Sources: ai-maestro:srch-pr.
- comments — Comments [unsupported]: No PR comments. Sources: ai-maestro:srch-pr.
- ci_response — Ci response [unsupported]: None. Sources: ai-maestro:srch-pr.
- rebase — Rebase [unsupported]: None. Sources: ai-maestro:srch-pr.
- conflicts — Conflicts [unsupported]: None. Sources: ai-maestro:srch-pr.
- product_state — Product state [partial]: Repos section on the agent profile lists repositories and remotes. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:readme, ai-maestro:diag, ai-maestro:commitrace, ai-maestro:srch-pr

### SHIP-04: Merge and deployment authority

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

No merge, release or deploy authority in the product; delivery happens through git by agents and humans, with no revision-bound approvals.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- approve: No approval flow.
- merge: No merge flow.
- release: None.
- deploy: Dashboard deploys agents to EC2/ECS, not user code.

- approve — Approve [unsupported]: No approval flow. Sources: ai-maestro:srch-pr.
- merge — Merge [unsupported]: No merge flow. Sources: ai-maestro:srch-pr.
- release — Release [unsupported]: None. Sources: ai-maestro:srch-pr.
- deploy — Deploy [partial]: Dashboard deploys agents to EC2/ECS, not user code. Sources: ai-maestro:cloud.
- exact_revision — Exact revision [unsupported]: None. Sources: ai-maestro:srch-pr.
- authority_enforcement — Authority enforcement [unsupported]: None. Sources: ai-maestro:srch-pr.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:srch-pr, ai-maestro:cloud

### SHIP-05: Completion evidence and rollback

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Commit-to-session tracing only; no PR, build or deployment links, delivery status, rollback or stale-approval handling.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- commit links: GET /api/commits/:sha finds the agent session (Claude Code only).
- pr links: A PR opened on GitHub cannot be traced.
- build links: None.
- deployment links: None.

- commit_links — Commit links [partial]: GET /api/commits/:sha finds the agent session (Claude Code only). Sources: ai-maestro:commitrace, ai-maestro:tasksdoc.
- pr_links — Pr links [unsupported]: A PR opened on GitHub cannot be traced. Sources: ai-maestro:tasksdoc.
- build_links — Build links [unsupported]: None. Sources: ai-maestro:srch-pr.
- deployment_links — Deployment links [unsupported]: None. Sources: ai-maestro:srch-pr.
- delivery_status — Delivery status [unsupported]: None. Sources: ai-maestro:srch-pr.
- retained_evidence — Retained evidence [partial]: Transcripts and commit index. Sources: ai-maestro:commitrace.
- rollback — Rollback [unsupported]: None. Sources: ai-maestro:srch-pr.
- revert — Revert [unsupported]: None. Sources: ai-maestro:srch-pr.
- stale_approval_invalidation — Stale approval invalidation [unsupported]: No approvals. Sources: ai-maestro:srch-pr.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:commitrace, ai-maestro:tasksdoc, ai-maestro:srch-pr

### SHIP-06: Batch review and high-volume shipping

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

No review queue or batch delivery features; Attention page lists cards in review and overdue work.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- review queue: Cards with status review appear on the Attention page.
- summaries: None.
- grouping: Matrix grouping by quadrant and Org view.
- risk size filters: None.

- review_queue — Review queue [partial]: Cards with status review appear on the Attention page. Sources: ai-maestro:tasksdoc.
- summaries — Summaries [unsupported]: None. Sources: ai-maestro:srch-review.
- grouping — Grouping [partial]: Matrix grouping by quadrant and Org view. Sources: ai-maestro:tasksdoc.
- risk_size_filters — Risk size filters [unsupported]: None. Sources: ai-maestro:srch-review.
- findings — Findings [unsupported]: None. Sources: ai-maestro:srch-review.
- artifacts — Artifacts [unsupported]: None. Sources: ai-maestro:srch-review.
- request_changes — Request changes [unsupported]: None. Sources: ai-maestro:srch-review.
- exact_revision_approval — Exact revision approval [unsupported]: None. Sources: ai-maestro:srch-pr.
- dependency_queues — Dependency queues [unsupported]: None. Sources: ai-maestro:taskreg.
- next_actions — Next actions [partial]: Attention page lists what needs you. Sources: ai-maestro:tasksdoc.
- stale_approval_invalidation — Stale approval invalidation [unsupported]: None. Sources: ai-maestro:srch-pr.
- check_deduplication — Check deduplication [unsupported]: None. Sources: ai-maestro:srch-review.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:tasksdoc, ai-maestro:srch-review, ai-maestro:srch-pr, ai-maestro:taskreg

## Ownership, privacy and economics

### OWN-01: Source and license

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

MIT for the dashboard and server (LICENSE, package.json); plugin skills and gateways are separate repositories; the iPhone and Android apps are closed; pinned v0.106.98 (3acb573).

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- hosted extensions: No hosted service exists.
- source visibility: Dashboard, plugin builder and gateways are public; mobile apps are not found in public repos.
- hosted parity: No hosted edition.

- client_license — Client license [supported]: Web dashboard code is MIT. Sources: ai-maestro:license, ai-maestro:pkg.
- server_license — Server license [supported]: server.mjs and services are MIT in the same repository. Sources: ai-maestro:license, ai-maestro:pkg.
- hosted_extensions — Hosted extensions [unsupported]: No hosted service exists. Sources: ai-maestro:readme.
- source_visibility — Source visibility [partial]: Dashboard, plugin builder and gateways are public; mobile apps are not found in public repos. Sources: ai-maestro:srch-clients, ai-maestro:gateways.
- source_revision — Source revision [supported]: v0.106.98 commit 3acb573. Sources: ai-maestro:release.
- hosted_parity — Hosted parity [not-applicable]: No hosted edition. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:license, ai-maestro:pkg, ai-maestro:readme, ai-maestro:srch-clients, ai-maestro:gateways, ai-maestro:release

### OWN-02: Hosting and exit

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Fully self-hosted with no vendor service; state is JSON/SQLite/CozoDB files under ~/.aimaestro; agents can be exported and imported as archives and transferred between hosts; transcript export exists.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- vendor dependencies: Version check hits raw.githubusercontent.com; optional TTS and Expo push use third parties; the iPhone app is distributed by Apple.
- formats: JSON files and archives.
- cancellation: No account exists to cancel.
- history portability: Transcripts export; memory graph is CozoDB.

- self_hosting — Self hosting [supported]: Runs entirely on user hosts, with headless workers. Sources: ai-maestro:readme.
- vendor_dependencies — Vendor dependencies [partial]: Version check hits raw.githubusercontent.com; optional TTS and Expo push use third parties; the iPhone app is distributed by Apple. Sources: ai-maestro:versioncheck, ai-maestro:pushexpo.
- export — Export [supported]: Export agent and transcript export dialogs. Sources: ai-maestro:readme.
- import — Import [supported]: Import agent dialog and aimaestro-task.sh import. Sources: ai-maestro:tasksdoc.
- formats — Formats [partial]: JSON files and archives. Sources: ai-maestro:schedreg.
- cancellation — Cancellation [not-applicable]: No account exists to cancel. Sources: ai-maestro:readme.
- account_independence — Account independence [supported]: No account. Sources: ai-maestro:readme.
- history_portability — History portability [partial]: Transcripts export; memory graph is CozoDB. Sources: ai-maestro:ltm.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:readme, ai-maestro:versioncheck, ai-maestro:pushexpo, ai-maestro:tasksdoc, ai-maestro:schedreg, ai-maestro:ltm

### OWN-03: Data handling and telemetry

Verification status: Sourced (sourced)
Support: partial

Everything stays on your hosts; the README states no telemetry, no account and no phone-home; Claude telemetry export is opt-in to your own receiver; optional TTS and push call third parties; the iPhone app sends crash reports unless disabled.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Version check is not documented as controllable.

- code_data — Code data [supported]: Code stays on user machines; model providers see what the CLI sends. Sources: ai-maestro:readme.
- prompts — Prompts [supported]: Prompts go to the user CLI's provider, not to AI Maestro servers. Sources: ai-maestro:readme.
- credentials — Credentials [supported]: aim-secret vault keeps credentials local. Sources: ai-maestro:secrets.
- logs — Logs [supported]: Logs stay local. Sources: ai-maestro:readme.
- artifacts — Artifacts [supported]: Artifacts stay local or in user-configured S3. Sources: ai-maestro:readme.
- retention — Retention [partial]: Local files; schedule executions capped at 50. Sources: ai-maestro:schedreg.
- deletion — Deletion [supported]: Users delete local files directly, and a per-memory DELETE route and button remove individual long-term memories. Sources: ai-maestro:memroute, ai-maestro:memviewer.
- training — Training [not-applicable]: No vendor model training. Sources: ai-maestro:readme.
- residency — Residency [supported]: Host-local. Sources: ai-maestro:readme.
- subprocessors — Subprocessors [partial]: Expo push and TTS vendors if enabled. Sources: ai-maestro:pushexpo.
- telemetry_disclosure — Telemetry disclosure [supported]: README FAQ says no telemetry and names the opt-in OTLP export. Sources: ai-maestro:readme, ai-maestro:telemetry.
- telemetry_defaults — Telemetry defaults [supported]: OTLP export is off unless AIMAESTRO_TELEMETRY is set; version check runs on load. Sources: ai-maestro:telemetry, ai-maestro:versioncheck.
- telemetry_controls — Telemetry controls [partial]: AIMAESTRO_TELEMETRY env; no setting to disable the version check was found. Sources: ai-maestro:telemetry, ai-maestro:versioncheck.
- consent_prompt — Consent prompt [unsupported]: No consent dialog. Sources: ai-maestro:readme.
- provider_separation — Provider separation [supported]: Model providers are separate (each CLI). Sources: ai-maestro:programs.

Checked 2026-11-16 (6 days old on 2026-11-22); not separately cross-checked.

Sources: ai-maestro:readme, ai-maestro:secrets, ai-maestro:schedreg, ai-maestro:memsvc, ai-maestro:pushexpo, ai-maestro:telemetry, ai-maestro:versioncheck, ai-maestro:programs, ai-maestro:memroute, ai-maestro:memviewer

### OWN-04: Price and included usage

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Free and MIT with no seats or usage fees; optional iPhone app is free for 30 days then $19.99 one-time (USD); agent subscriptions and your cloud costs are separate.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Free MIT; optional iPhone app; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- included usage: No metered usage.
- credits: No credits.
- overages: None.
- taxes: Tax treatment on the App Store purchase is not stated.

- currency — Currency [supported]: USD for the iPhone app ($19.99). Sources: ai-maestro:iphonepage.
- interval — Interval [supported]: One-time purchase for the app; nothing recurring. Sources: ai-maestro:iphonepage.
- seats — Seats [supported]: No seats. Sources: ai-maestro:readme.
- seat_minimum — Seat minimum [supported]: None. Sources: ai-maestro:readme.
- workspace_fees — Workspace fees [supported]: None. Sources: ai-maestro:readme.
- included_usage — Included usage [not-applicable]: No metered usage. Sources: ai-maestro:readme.
- credits — Credits [unsupported]: No credits. Sources: ai-maestro:readme.
- trial — Trial [supported]: iPhone app has a 30-day free trial. Sources: ai-maestro:iphonepage.
- overages — Overages [not-applicable]: None. Sources: ai-maestro:readme.
- taxes — Taxes [unknown]: Tax treatment on the App Store purchase is not stated. Sources: ai-maestro:iphonepage.
- model_cost — Model cost [supported]: Paid separately to each CLI provider. Sources: ai-maestro:readme.
- compute_cost — Compute cost [supported]: Paid to your cloud or hardware. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:iphonepage, ai-maestro:readme

### OWN-05: Scenario cost and controls

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Scenario costs are not priced by the vendor; the ADE is free, so only CLI subscriptions, hardware or cloud and the optional $19.99 app apply; no invented averages.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- one person: ADE $0 plus the user's agent subscriptions and optional $19.99 app.
- two people: No multi-user pricing; each person would use their own hosts.
- five people: Same; no seat pricing.
- task assumptions: No vendor scenario.

- one_person — One person [partial]: ADE $0 plus the user's agent subscriptions and optional $19.99 app. Sources: ai-maestro:readme, ai-maestro:iphonepage.
- two_people — Two people [partial]: No multi-user pricing; each person would use their own hosts. Sources: ai-maestro:readme, ai-maestro:product.
- five_people — Five people [partial]: Same; no seat pricing. Sources: ai-maestro:readme.
- task_assumptions — Task assumptions [not-applicable]: No vendor scenario. Sources: ai-maestro:readme.
- concurrency — Concurrency [not-applicable]: No vendor scenario. Sources: ai-maestro:readme.
- tokens — Tokens [not-applicable]: Not metered by the ADE. Sources: ai-maestro:readme.
- compute_hours — Compute hours [partial]: Linux sizing guide gives RAM/CPU for hosts but no hours. Sources: ai-maestro:readme.
- fixed_cost — Fixed cost [supported]: ADE fixed cost is zero. Sources: ai-maestro:readme.
- variable_cost — Variable cost [partial]: Variable cost is the CLI subscription or API usage. Sources: ai-maestro:readme.
- included_cost — Included cost [not-applicable]: None included. Sources: ai-maestro:readme.
- unknown_cost — Unknown cost [partial]: Cloud and model usage are unknown by design. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:readme, ai-maestro:iphonepage, ai-maestro:product

### OWN-06: Availability and support

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Generally available open-source releases at a high cadence (v0.106.98 on 2026-11-07); support is through GitHub issues; no response commitments or status page found; iPhone app on the App Store, Android in invite beta.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- access restrictions: Android is an email-invited beta.
- support: GitHub issues and support email for app testers.
- response commitments: None stated.
- status history: No status page.

- release_stage — Release stage [supported]: Release v0.106.98 and App Store version 1.0.5; version numbers below 1.0 for the server. Sources: ai-maestro:release, ai-maestro:appstore.
- access_restrictions — Access restrictions [partial]: Android is an email-invited beta. Sources: ai-maestro:iphonepage.
- support — Support [partial]: GitHub issues and support email for app testers. Sources: ai-maestro:readme, ai-maestro:iphonepage.
- response_commitments — Response commitments [unsupported]: None stated. Sources: ai-maestro:readme.
- release_activity — Release activity [supported]: Frequent dated releases and commits through 2026-11-10. Sources: ai-maestro:changelog, ai-maestro:repoapi.
- status_history — Status history [unsupported]: No status page. Sources: ai-maestro:readme.
- deprecation — Deprecation [partial]: Aider deprecated in the program list. Sources: ai-maestro:programs.
- export_options — Export options [supported]: Local files and archives. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:release, ai-maestro:appstore, ai-maestro:iphonepage, ai-maestro:readme, ai-maestro:changelog, ai-maestro:repoapi, ai-maestro:programs

### OWN-07: Enterprise assurance

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

No ISO or SOC 2 claims are published for this MIT project; SECURITY.md lists advisories and the network trust model.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- iso scope: No ISO certificate claim found in the repository, SECURITY.md or website.
- iso issuer: No public certification statement or report found in the checked sources.
- iso validity: No public certification statement or report found in the checked sources.
- soc2 type: No SOC 2 report claim found in the repository, SECURITY.md or website.

- iso_scope — Iso scope [unknown]: No ISO certificate claim found in the repository, SECURITY.md or website. Sources: ai-maestro:security.
- iso_issuer — Iso issuer [unknown]: No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
- iso_validity — Iso validity [unknown]: No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
- soc2_type — Soc2 type [unknown]: No SOC 2 report claim found in the repository, SECURITY.md or website. Sources: ai-maestro:security.
- soc2_scope — Soc2 scope [unknown]: No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
- soc2_period — Soc2 period [unknown]: No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
- report_access — Report access [unknown]: No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
- verification_date — Verification date [unknown]: No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
- evidence_status — Evidence status [partial]: Public advisories and a security policy exist; no attestations. Sources: ai-maestro:security.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:security

### OWN-08: Useful free tier and evaluation access

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Free to use in full as MIT software with no card; iPhone app has a 30-day trial then $19.99 one-time; Android beta by invitation.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- credits trial: None.
- paid only: No paid-only core.
- early access: Android beta by invitation.
- free scenarios: Everything except mobile apps works free; iPhone is a free trial.

- ongoing_free — Ongoing free [supported]: Whole product is free. Sources: ai-maestro:readme.
- trial — Trial [supported]: iPhone app 30-day trial. Sources: ai-maestro:iphonepage.
- credits_trial — Credits trial [not-applicable]: None. Sources: ai-maestro:readme.
- self_host_cost — Self host cost [supported]: Hardware plus CLI subscriptions. Sources: ai-maestro:readme.
- paid_only — Paid only [not-applicable]: No paid-only core. Sources: ai-maestro:readme.
- early_access — Early access [partial]: Android beta by invitation. Sources: ai-maestro:iphonepage.
- free_scenarios — Free scenarios [partial]: Everything except mobile apps works free; iPhone is a free trial. Sources: ai-maestro:readme, ai-maestro:iphonepage.
- card_required — Card required [not-applicable]: None for the ADE. Sources: ai-maestro:readme.
- usage_caps — Usage caps [supported]: None. Sources: ai-maestro:readme.
- paid_evaluation — Paid evaluation [not-applicable]: No. Sources: ai-maestro:readme.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:readme, ai-maestro:iphonepage

### OWN-09: Pricing transparency

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Transparent: free MIT software, no seats or usage fees; the only price is the one-time $19.99 iPhone app after a 30-day trial; model and compute costs are the user's.

Availability: generally-available
Delivery: native
Scope: surfaces=Web dashboard and headless server (localhost:23000, tmux agents); version=v0.106.98 (commit 3acb573, released 2026-11-07); plan=Open source (MIT); os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- overages: None.
- compute markup: No markup; user pays cloud directly.
- model markup: No markup.
- cancellation: Nothing recurring.

- units — Units [supported]: One-time app purchase; nothing else. Sources: ai-maestro:iphonepage, ai-maestro:readme.
- included_limits — Included limits [supported]: None. Sources: ai-maestro:readme.
- overages — Overages [not-applicable]: None. Sources: ai-maestro:readme.
- compute_markup — Compute markup [not-applicable]: No markup; user pays cloud directly. Sources: ai-maestro:readme.
- model_markup — Model markup [not-applicable]: No markup. Sources: ai-maestro:readme.
- minimum_commitment — Minimum commitment [supported]: None. Sources: ai-maestro:readme.
- cancellation — Cancellation [not-applicable]: Nothing recurring. Sources: ai-maestro:iphonepage.
- sales_only_unknowns — Sales only unknowns [not-applicable]: No sales-only plans. Sources: ai-maestro:readme.
- transparency_classification — Transparency classification [supported]: Transparent. Sources: ai-maestro:readme, ai-maestro:iphonepage.

Checked 2026-11-16 (6 days old on 2026-11-22); agent cross-checked 2026-11-17.

Sources: ai-maestro:iphonepage, ai-maestro:readme

## Sources

### ai-maestro:readme

AI Maestro README. MIT dashboard for tmux-hosted coding agents across a peer mesh; Claude Code/Codex/Grok Build first-class, Pi/OpenClaw/Copilot CLI launch only; Windows via WSL2; no telemetry; no hosted tier; iPhone app listed as coming soon in this README.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/README.md
- Locator: Quick Start; Features; Agent Deployment; FAQ
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:programs

docs/AGENT-PROGRAMS.md. Per-program support: Claude Code, Codex CLI, Grok Build get launch, chat history, status and approval cards; Pi, Copilot CLI, OpenClaw recognised with limits; Cursor, Gemini CLI, OpenCode have no reader; Aider deprecated.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/docs/AGENT-PROGRAMS.md
- Locator: support matrix table; Grok Build; Codex CLI; Pi; GitHub Copilot CLI; OpenClaw; Anything else
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:manifest

app/manifest.ts. Web app manifest (display standalone) so a browser can install the dashboard as an app on https or localhost; phones can Add to Home Screen.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/app/manifest.ts
- Locator: manifest()
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: app/manifest.ts

### ai-maestro:pushexpo

lib/push-expo.ts. Host sends a thin push (agent name and fixed sentence) through Expo push service to a registered phone token; one push per agent per type per 60 s.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/push-expo.ts
- Locator: SEND_URL, header comment, COOLDOWN_MS
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/push-expo.ts

### ai-maestro:iphonepage

ai-maestro-website iphone.html. iPhone app on the App Store (30 days free, then $19.99 one-time) lets you see status, answer permission prompts and questions, chat, open a terminal and start agents; Android 7+ is a beta joined by emailing support; the app needs AI Maestro running on a computer you control.

- URL: https://github.com/23blocks-OS/ai-maestro-website/blob/7b49891214429a8d7581080782ea59360fc6f7e5/iphone.html
- Locator: schema.org MobileApplication; "When can I get it?"; Android answer
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:appstore

AI Maestro on the App Store. App Store listing "AI Maestro" by 23blocks Inc, version 1.0.5 (updated 2026-11-14), first released 2026-11-06, minimum iOS 15.1, listed price Free.

- URL: https://apps.apple.com/us/app/ai-maestro/id6823011943
- Locator: iTunes lookup API id6823011943: trackName, version, minimumOsVersion, releaseDate, price
- Evidence kind: documented
- Source date: 2026-11-14
- Retrieved: 2026-11-16

### ai-maestro:reqs

docs/REQUIREMENTS.md. Minimum macOS 12.0, recommended 13, tested on 14+.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/docs/REQUIREMENTS.md
- Locator: macOS section; hardware
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:quickstart

docs/QUICKSTART.md. macOS 12+, Windows 10+ via WSL2, or Linux; Node and tmux.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/docs/QUICKSTART.md
- Locator: Prerequisites
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:security

SECURITY.md. Binds 0.0.0.0:23000 with no application-level authentication by design (network is the perimeter); tmux sessions persist after the dashboard closes and run as the user; two tmux command-injection CVEs fixed.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/SECURITY.md
- Locator: Network Access Configuration; By design no authentication; tmux Session Security; Resolved Advisories
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:concepts

docs/CONCEPTS.md. Peer mesh with no central server; each agent is a tmux session plus working directory; agents own repositories and are not given shared working copies.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/docs/CONCEPTS.md
- Locator: Peer Mesh Network; Agents and tmux Sessions; Agent Ownership
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:product

PRODUCT.md. Primary user is a solo operator; "Not currently designed for multiple humans sharing one fleet (no attribution or handoff model exists)"; no authentication by design; responsive desktop, tablet and phone layouts.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/PRODUCT.md
- Locator: Users; Capabilities and Constraints
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:tasksdoc

docs/TASKS.md. Cards on agent, team and project boards with status, blockedBy, quadrant, kind (task/idea/bug/research), origin, due, owners; Matrix, Org and Attention pages; agent CLI and REST API; commit-to-session trace for Claude Code sessions only.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/docs/TASKS.md
- Locator: What a card holds; For agents: aimaestro-task.sh; API; Commit to session
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:plugscripts

ai-maestro-plugins plugins/ai-maestro/scripts. Plugin ships CLI scripts for agent management, tasks, AMP messaging, identity, files and device control used by 14 skills.

- URL: https://github.com/23blocks-OS/ai-maestro-plugins/blob/574746cba900ba2c5b4dd9318de7a1fe140580da/plugins/ai-maestro/scripts
- Locator: directory listing: aimaestro-agent.sh, aimaestro-task.sh, amp-send.sh, aimaestro-call.sh
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 574746cba900ba2c5b4dd9318de7a1fe140580da
- Path: plugins/ai-maestro/scripts

### ai-maestro:srch-clients

Bounded search: clients. No Electron, Tauri, VS Code or JetBrains extension; only a web app, PWA manifest and Expo push; the iOS and Android apps are not in the public repositories.

- URL: https://github.com/23blocks-OS/ai-maestro/tree/3acb573466ccf28ed1d044ae85c528320734d220
- Locator: grep -Ei over app, lib, services, components, package.json for electron, tauri, vsix, jetbrains plugin, vscode extension
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: .

### ai-maestro:pkg

package.json. ai-maestro 0.106.98, MIT, Node >=22; scripts dev/start/headless (MAESTRO_MODE=headless tsx server.mjs); dependencies include @anthropic-ai/claude-agent-sdk, xterm, node-pty, cozo-node, cron-parser.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/package.json
- Locator: name, version, license, engines, scripts.dev/headless, dependencies
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: package.json

### ai-maestro:prognames

lib/program-names.ts. ProgramKind: claude, codex, aider, cursor, gemini, opencode, openclaw, grok, pi, copilot, wrapper.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/program-names.ts
- Locator: ProgramKind union
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/program-names.ts

### ai-maestro:chatarch

docs/CHAT-ARCHITECTURE.md. Default tmux chat path types into the terminal and reads the screen; the Streaming tab uses the Claude Agent SDK with structured events and canUseTool approvals.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/docs/CHAT-ARCHITECTURE.md
- Locator: There are TWO chat paths; Why the SDK path
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:hook

scripts/claude-hooks/ai-maestro-hook.cjs. One hook script for Claude Code (Stop, Notification idle_prompt, SessionStart, UserPromptSubmit), Codex (Stop, SessionStart), Gemini and Grok; delivers unread AMP messages and reports working/idle/needs-you status.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/scripts/claude-hooks/ai-maestro-hook.cjs
- Locator: header comment events; supportsStopBlock; isStopHookActive
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: scripts/claude-hooks/ai-maestro-hook.cjs

### ai-maestro:programlaunch

lib/program-command.ts. Builds each program launch command and its permission flags (e.g. --permission-mode, --always-approve, --allow-all-tools).

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/program-command.ts
- Locator: launch flags per program
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/program-command.ts

### ai-maestro:srch-billing

Bounded search: billing. No billing or licence-gating code in the open-source server.

- URL: https://github.com/23blocks-OS/ai-maestro/tree/3acb573466ccf28ed1d044ae85c528320734d220
- Locator: grep -Ei for stripe, license key, paywall, subscription plan
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: .

### ai-maestro:srch-acct

lib/cozo-schema.ts. Bounded grep finds no account-switching feature; the only hit is a stored claude_config_dir path per project.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/cozo-schema.ts
- Locator: grep -rniE "CLAUDE_CONFIG_DIR|multiple accounts|switch account" lib services docs README.md
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-17
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/cozo-schema.ts

### ai-maestro:docker

services/agents-docker-service.ts. Docker agents run in a container with dropped capabilities, no-new-privileges, noexec tmpfs, CPU and memory limits (default 2 CPUs, 4g) and a bind-mounted workspace.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/services/agents-docker-service.ts
- Locator: dockerArgs: --cap-drop=ALL, --security-opt no-new-privileges, --cpus, --memory, -v workDir:/workspace
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: services/agents-docker-service.ts

### ai-maestro:cloud

services/agents-cloud-service.ts. Cloud agents are created through Terraform modules (EC2 and ECS Fargate) in the user's own AWS account.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/services/agents-cloud-service.ts
- Locator: checkTerraformAvailable, copyTerraformModule
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: services/agents-cloud-service.ts

### ai-maestro:tfreadme

infrastructure/terraform/aws-agent/README.md. EC2 deployment needs an AWS account, AWS CLI, Terraform, key pair, ECR image, GitHub token and a domain for SSL.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/infrastructure/terraform/aws-agent/README.md
- Locator: Prerequisites; Quick Start
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:channel

lib/amp-channel-server.mjs. An MCP server (claude/channel capability, stdio) that Claude Code spawns to push AMP inbox events into a running session; registers a localhost port under ~/.aimaestro/channels.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/amp-channel-server.mjs
- Locator: file header
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/amp-channel-server.mjs

### ai-maestro:webhooks

lib/webhook-service.ts. Signed webhook subscriptions (whsec_ secrets) stored in ~/.aimaestro/webhooks.json.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/webhook-service.ts
- Locator: WEBHOOKS_FILE, generateSecret
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/webhook-service.ts

### ai-maestro:ampauth

lib/amp-auth.ts. AMP API keys (amp_live_sk_...) stored hashed with rotation and a 24 h grace period.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/amp-auth.ts
- Locator: KEY_PREFIX_LIVE, API_KEYS_FILE
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/amp-auth.ts

### ai-maestro:srch-stab

README.md. Bounded grep finds no API stability or deprecation policy for the dashboard REST API; package.json is 0.106.x and only the AMP routes carry an /api/v1 prefix.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/README.md
- Locator: grep -niE "stable|deprecat|breaking|semver|api version" README.md docs/*.md SECURITY.md
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-17
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: README.md

### ai-maestro:progchoices

lib/program-choices.ts. Permission modes per program: Claude and Grok get five modes, Codex four, Copilot two; Pi none.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/program-choices.ts
- Locator: MODES_BY_KIND, ALL_PERMISSION_MODES
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/program-choices.ts

### ai-maestro:teamtype

types/team.ts. Teams (open or closed) with agentIds, instructions markdown, chiefOfStaffId; persistent meetings link to team task boards.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/types/team.ts
- Locator: Team, TeamType, Meeting
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: types/team.ts

### ai-maestro:secrets

docs/SECRETS.md. aim-secret vault (Keychain, libsecret or encrypted file); agent uses secrets by name with values scrubbed; file backend protects against accidents only.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/docs/SECRETS.md
- Locator: Use; Where the value lives
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:plugskills

ai-maestro-plugins plugins/ai-maestro/skills. Skills: agent-actions, agent-devices, agent-files, agent-identity, agent-messaging, agent-tasks, agents-management, aim-secret-management, docs-search, graph-query, memory-search, planning, agentic-sql/seo/support, call-a-person.

- URL: https://github.com/23blocks-OS/ai-maestro-plugins/blob/574746cba900ba2c5b4dd9318de7a1fe140580da/plugins/ai-maestro/skills
- Locator: directory listing
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 574746cba900ba2c5b4dd9318de7a1fe140580da
- Path: plugins/ai-maestro/skills

### ai-maestro:gateways

aimaestro-gateways README. Separate repository: Slack, Discord, Email and WhatsApp gateways for AI Maestro agents with prompt-injection filtering and trust levels.

- URL: https://github.com/23blocks-OS/aimaestro-gateways/blob/5da6b3d957047bf5b513570e1e248fbc585a2e6b/README.md
- Locator: overview
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:tasktype

types/task.ts. Status backlog/pending/in_progress/review/waiting/completed; comments with author kind operator or agent; blockedBy, waitingOn, due, owners, result.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/types/task.ts
- Locator: TaskStatus, Task, TaskComment
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: types/task.ts

### ai-maestro:taskreg

lib/task-registry.ts. blockedBy is stored on each card; isBlocked and blocks are derived; cycles are refused; completing a card returns newly unblocked cards. No dispatch gate on blockers found.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/task-registry.ts
- Locator: resolveTaskDeps, updateScopeTask, wouldCreateScopeCycle
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/task-registry.ts

### ai-maestro:sched

lib/schedule-executor.ts. Dashboard-side cron scheduler checks due schedules every 60 s and types the prompt into the agent session (starting it if needed).

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/schedule-executor.ts
- Locator: CHECK_INTERVAL_MS, startScheduler, runningExecutions
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/schedule-executor.ts

### ai-maestro:srch-pr

Bounded search: pr. No pull request creation or review code; only commit-to-session tracing and a GitHub token passed to Docker/EC2 agents for git push.

- URL: https://github.com/23blocks-OS/ai-maestro/tree/3acb573466ccf28ed1d044ae85c528320734d220
- Locator: grep -Ei for createPullRequest, gh pr create, octokit, /pulls, pull_request
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: .

### ai-maestro:tasksvc

services/agent-tasks-service.ts. A card assigned to an agent can be forwarded as a typed instruction to the assignee agent session on another host (POST /api/agents/:id/task-instruction).

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/services/agent-tasks-service.ts
- Locator: sendInstruction, receiveInstruction, assigneeOk
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: services/agent-tasks-service.ts

### ai-maestro:commitrace

lib/commit-trace.ts. Maps a git commit to the Claude Code agent session that made it; GET /api/commits/:sha.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/commit-trace.ts
- Locator: file header
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/commit-trace.ts

### ai-maestro:agenttype

types/agent.ts. Agent roles manager/chief-of-staff/member for messaging policy; metrics tiles with totalTokensUsed and estimatedCost.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/types/agent.ts
- Locator: AgentRole, Agent.metrics, estimatedCost, totalTokensUsed
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: types/agent.ts

### ai-maestro:ltm

docs/LONG-TERM-MEMORY.md. Opt-in per-agent long-term memory: nightly consolidation into memory cards and an entity graph, recall injected into prompts; secrets redacted.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/docs/LONG-TERM-MEMORY.md
- Locator: Concepts; consolidation 2 AM; recall
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:memsvc

services/agents-memory-service.ts. REST memory API per agent (GET and POST); no delete route in app/api/agents/[id]/memory.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/services/agents-memory-service.ts
- Locator: getMemory, initializeMemory
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: services/agents-memory-service.ts

### ai-maestro:memroute

app/api/agents/[id]/memory/long-term/route.ts. Per-agent long-term memory API: DELETE removes one memory by id and PATCH edits content, category and context.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/app/api/agents/[id]/memory/long-term/route.ts
- Locator: GET, DELETE ?id=, PATCH handlers
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-17
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: app/api/agents/[id]/memory/long-term/route.ts

### ai-maestro:memviewer

components/MemoryViewer.tsx. MemoryViewer lists memories and offers a per-memory delete button that calls the DELETE route after a confirm prompt.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/components/MemoryViewer.tsx
- Locator: deleteMemory; per-memory Delete button
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-17
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: components/MemoryViewer.tsx

### ai-maestro:srch-review

Bounded search: review. No diff or code review component; Work/Worktree tabs show repository and conversation info.

- URL: https://github.com/23blocks-OS/ai-maestro/tree/3acb573466ccf28ed1d044ae85c528320734d220
- Locator: grep -Ei for diff2html, react-diff, unified diff, git diff over components and services
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: .

### ai-maestro:matrixpage

app/matrix/page.tsx. The Matrix page filters cards by agent name or alias; no free-text search over card subjects or descriptions was found in app/matrix, components/matrix or AgentBoardPanel.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/app/matrix/page.tsx
- Locator: agentFilter state and cardMatchesAgent
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-17
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: app/matrix/page.tsx

### ai-maestro:srch-taskcas

lib/task-registry.ts. Tasks are read-modify-written as a JSON file synchronously in one process; the grep found no lock, version check or merge step, so concurrent writers would overwrite each other.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/task-registry.ts
- Locator: writeFileSync at line 71; grep for lock|mutex|etag|expectedVersion
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-17
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/task-registry.ts

### ai-maestro:ampsvc

services/amp-service.ts. AMP routing is rate limited to 60 messages per minute per agent.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/services/amp-service.ts
- Locator: ROUTE_RATE_LIMIT_MAX
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: services/amp-service.ts

### ai-maestro:srch-budget

Bounded search: budget. No per-agent time, turn, token or spend limit; only tmux/hook timeouts, AMP rate limit and Docker CPU/memory limits.

- URL: https://github.com/23blocks-OS/ai-maestro/tree/3acb573466ccf28ed1d044ae85c528320734d220
- Locator: grep -Ei for maxBudget, max-budget, maxTurns, max_turns, spend limit, token limit, timeout per task
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: .

### ai-maestro:diag

services/diagnostics-service.ts. Diagnostics warn when more than one agent uses the same folder and suggest a separate folder or git worktree.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/services/diagnostics-service.ts
- Locator: shared folder check
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: services/diagnostics-service.ts

### ai-maestro:schedreg

lib/schedule-registry.ts. Schedules stored in ~/.aimaestro/schedules.json with cron expressions and timezone; last 50 executions kept per schedule.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/schedule-registry.ts
- Locator: SCHEDULES_FILE, cron-parser, MAX_EXECUTIONS_PER_SCHEDULE
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/schedule-registry.ts

### ai-maestro:agentsched

lib/agent-schedule-runner.ts. Per-agent schedules fire when the agent goes idle, skip when a run is in flight and back off after errors instead of retrying on every idle.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/agent-schedule-runner.ts
- Locator: inFlight, backoff comment, skipped
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/agent-schedule-runner.ts

### ai-maestro:tfvars

infrastructure/terraform/aws-agent/variables.tf. EC2 agent Terraform module takes an aws_region variable (default us-east-1) chosen by the user.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/infrastructure/terraform/aws-agent/variables.tf
- Locator: variable aws_region
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-17
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: infrastructure/terraform/aws-agent/variables.tf

### ai-maestro:srch-sandbox

Bounded search: sandbox. OS sandboxing exists only as launch flags for supported CLIs and as the Docker agent runtime; tmux agents run as the host user.

- URL: https://github.com/23blocks-OS/ai-maestro/tree/3acb573466ccf28ed1d044ae85c528320734d220
- Locator: grep -Ei for sandbox, bubblewrap, seatbelt in services and lib
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: .

### ai-maestro:costscript

scripts/cost-breakdown.mjs. Offline script reads Claude Code transcripts and reports shares of cost by cache read/write/output tokens; proportions, not dollars.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/scripts/cost-breakdown.mjs
- Locator: file header
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: scripts/cost-breakdown.mjs

### ai-maestro:telsvc

services/telemetry-service.ts. Receiver maps Claude Code session.id metrics to an agent and fills token and cost tiles.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/services/telemetry-service.ts
- Locator: metrics.totalTokensUsed, estimatedCost
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: services/telemetry-service.ts

### ai-maestro:telemetry

lib/claude-telemetry.ts. Off by default: AIMAESTRO_TELEMETRY opts Claude Code launches into exporting OTLP metrics to the local AI Maestro receiver (or a central collector the operator sets).

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/lib/claude-telemetry.ts
- Locator: isTelemetryEnabled, claudeTelemetryEnvPrefix
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: lib/claude-telemetry.ts

### ai-maestro:srch-sso

Bounded search: sso. No SSO, SCIM, login or membership code; the only roles are agent messaging roles (manager, chief-of-staff, member) and AMP/AID agent identity.

- URL: https://github.com/23blocks-OS/ai-maestro/tree/3acb573466ccf28ed1d044ae85c528320734d220
- Locator: grep -Ei for saml, oidc, openid, scim, sso, oauth login, organization roles
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: .

### ai-maestro:auditspec

docs/SPEC-AUDIT-TRAIL.md. Audit trail is a draft spec: "Nothing here is built"; planned hash-chained per-agent log, off by default.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/docs/SPEC-AUDIT-TRAIL.md
- Locator: Status line; Rules; Section 8
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:qs-keys

docs/QUICKSTART.md Keyboard Shortcuts. Documented shortcuts are terminal scroll (Shift+PageUp/PageDown) and copy/paste only; no review or approval shortcuts.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/docs/QUICKSTART.md
- Locator: Keyboard Shortcuts table
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-17
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: docs/QUICKSTART.md

### ai-maestro:license

LICENSE. MIT License text for the whole repository.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/LICENSE
- Locator: whole file
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: LICENSE

### ai-maestro:release

AI Maestro v0.106.98 release. Release v0.106.98 "Agents get their own devices and a voice; chat search and reactions; the Doctor" published 2026-11-07.

- URL: https://github.com/23blocks-OS/ai-maestro/releases/tag/v0.106.98
- Locator: release notes
- Evidence kind: documented
- Source date: 2026-11-07
- Retrieved: 2026-11-16

### ai-maestro:versioncheck

components/VersionChecker.tsx. The dashboard fetches version.json from raw.githubusercontent.com to show an update notice.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/components/VersionChecker.tsx
- Locator: REMOTE_VERSION_URL
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: components/VersionChecker.tsx

### ai-maestro:repoapi

GitHub repository metadata. 853 stars on the main repository (23blocks-OS/ai-maestro), MIT, pushed 2026-11-10; latest release v0.106.98 published 2026-11-07.

- URL: https://api.github.com/repos/23blocks-OS/ai-maestro
- Locator: stargazers_count, license, pushed_at
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### ai-maestro:changelog

CHANGELOG.md. Changelog records frequent releases (0.106.x series) with dated entries; used for roadmap and release-activity checks.

- URL: https://github.com/23blocks-OS/ai-maestro/blob/3acb573466ccf28ed1d044ae85c528320734d220/CHANGELOG.md
- Locator: top entries
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: 3acb573466ccf28ed1d044ae85c528320734d220
- Path: CHANGELOG.md
