podium

AI Maestro

51 of 51 criteria have a sourced finding; 42 were also cross-checked by a second agent. Every comparison that includes AI Maestro links here for scope, limitations, atomic answers and sources.

Humans approve the rubric, templates and prototype; they do not review every finding. An agent source cross-check is not a hands-on product test. A missing sourced finding is not evidence that a capability is absent.

Rubric
0.3 · 51 criteria
Source checks
2026-11-16
Agent cross-checked
42 criteria
Comparisons
1

Access and agent choice

ACC-01

Client access

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • Windows only through WSL2.
  • Mobile apps are closed source and Android is an invite-only beta.
  • No editor extension.
9 atomic answers
  • 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 [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 [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 [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 [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 [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 [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 [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 [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.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • Support depth differs per CLI.
  • No custom adapter interface; each reader is built into the server.
5 atomic answers
  • 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 [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 [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 [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 [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.

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

Sourced 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • No account switching in AI Maestro itself; each host uses the login its CLI holds.
7 atomic answers
  • 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 [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 [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 [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 [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 [supported] No AI Maestro account or login is required ("No account, no telemetry"). Sources: ai-maestro:readme.
  • 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.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • Manual steps for installing each CLI and logging in on every host.
7 atomic answers
  • 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 [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 [supported] Repos are discovered by .git presence and read with git config; a remote origin is optional. Sources: ai-maestro:concepts.
  • 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 [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 [unsupported] No vendor-managed cloud exists ("Is there a hosted / cloud version? Not yet"). Sources: ai-maestro:readme.
  • 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.

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

Sourced 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • Unauthenticated dashboard API by design.
  • No SDK.
8 atomic answers
  • 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 [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 [unsupported] No client SDK is published in the inspected repositories. Sources: ai-maestro:srch-clients.
  • 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 [supported] Webhook subscriptions with whsec_ signing secrets for agent and email events. Sources: ai-maestro:webhooks.
  • 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 [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 [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.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • Mostly inherited from each CLI.
7 atomic answers
  • 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 [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 [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 [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 [partial] Integration credentials go through aim-secret (vault) or each tool's own login. Sources: ai-maestro:secrets.
  • 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 [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.

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

Agent cross-checked 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").

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • Mobile client implementation not public.
4 atomic answers
  • 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 [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 [supported] Web UI plus PWA install; no hybrid wrapper in the repository. Sources: ai-maestro:manifest.
  • Implementation evidence [partial] Pinned package.json and source cover the web app; mobile builds are closed. Sources: ai-maestro:pkg, ai-maestro:appstore.

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

Planning and context

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
9 atomic answers
  • Local creation [supported] Cards are created from the dashboard, aimaestro-task.sh add/park and the REST API. Sources: ai-maestro:tasksdoc.
  • Prompt intake [supported] Prompts go through chat or typed instructions; schedules can issue prompts. Sources: ai-maestro:chatarch, ai-maestro:sched.
  • 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 [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 [supported] The JSON board files in the user's ~/.aimaestro are authoritative; no external tracker is linked. Sources: ai-maestro:taskreg.
  • Stable ids [supported] Cards have UUIDs (short prefix shown in instructions). Sources: ai-maestro:taskreg.
  • Sync [unsupported] No external tracker sync exists in the inspected code. Sources: ai-maestro:srch-pr.
  • Supported edits [supported] Edit subject, description, status, priority, assignee, owners, due, quadrant, waiting and blockers. Sources: ai-maestro:tasktype.
  • External roundtrips [not-applicable] Not applicable: nothing is synced to an external tracker. Sources: ai-maestro:srch-pr.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
7 atomic answers
  • 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 [unsupported] No acceptance-criteria field on cards in the inspected types. Sources: ai-maestro:tasktype.
  • Editors [supported] Card detail and board edit description and fields in the dashboard. Sources: ai-maestro:tasksdoc.
  • Revisions [unsupported] Cards store comments but no edit history. Sources: ai-maestro:tasktype.
  • Amendment [supported] A card can be edited while its agent works; instructions can be resent. Sources: ai-maestro:tasksvc.
  • Restart persistence [supported] Boards are JSON files on disk that survive server restarts. Sources: ai-maestro:taskreg.

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

Sourced 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • 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.
9 atomic answers
  • Epics [unsupported] No epic or parent field on cards; teams and projects are containers. Sources: ai-maestro:tasktype, ai-maestro:teamtype.
  • Hierarchy [unsupported] Card hierarchy is not modelled; agents have a manager hierarchy and org chart instead. Sources: ai-maestro:tasktype, ai-maestro:agenttype.
  • Blockers [supported] blockedBy lists of card IDs with a derived blocks list and isBlocked flag. Sources: ai-maestro:taskreg.
  • 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 [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 [partial] Completion returns the unblocked cards but does not move them. Sources: ai-maestro:taskreg.
  • Task to epic [unsupported] No epic concept to grow into. Sources: ai-maestro:tasktype.
  • 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 [supported] No rigid workflow is required; any status can be set. Sources: ai-maestro:tasktype.

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

Sourced 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • Memory is opt-in per agent and team memory is not shared by default.
10 atomic answers
  • 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 [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 [supported] Docs skill and DocumentationPanel index generated documentation of the agent codebase. Sources: ai-maestro:readme.
  • 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 [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 [supported] Each memory statement is backed by the passages it came from. Sources: ai-maestro:readme, ai-maestro:ltm.
  • 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 [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 [supported] Ended relations are marked and recurrence weights knowledge; nightly consolidation keeps it current. Sources: ai-maestro:readme, ai-maestro:ltm.
  • Takeover continuity [supported] Memory and agent identity survive new sessions and agent transfer between hosts. Sources: ai-maestro:readme, ai-maestro:concepts.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
10 atomic answers
  • Indexing [supported] Delta indexing of the codebase graph and transcripts (index-delta route). Sources: ai-maestro:readme.
  • External knowledge [partial] Plugin personalities and gateways; no connector to external knowledge bases in core. Sources: ai-maestro:readme, ai-maestro:gateways.
  • Multimodal inputs [partial] Agent uploads and AMP attachments exist; image reasoning depends on the CLI. Sources: ai-maestro:srch-review.
  • Freshness [supported] Delta index updates and nightly memory runs. Sources: ai-maestro:readme, ai-maestro:ltm.
  • Access scope [supported] Per-agent indexes keyed to the agent working directory. Sources: ai-maestro:readme.
  • Api retrieval [supported] REST routes for graph, docs, memory and search per agent. Sources: ai-maestro:readme.
  • Citations [partial] Memory cards cite passages; graph answers list callers and dependencies. Sources: ai-maestro:ltm.
  • Conflict detection [unsupported] No conflict-detection logic found. Sources: ai-maestro:srch-review.
  • Review enforcement [unsupported] No review-time architectural enforcement. Sources: ai-maestro:srch-review.

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

Sourced 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • 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.
17 atomic answers
  • Create [supported] Create from dashboard, CLI and API. Sources: ai-maestro:tasksdoc.
  • Edit [supported] Edit all card fields. Sources: ai-maestro:tasktype.
  • Discuss [supported] Comments with operator or agent authors. Sources: ai-maestro:tasktype.
  • Prioritize [supported] priority and urgent/important quadrant. Sources: ai-maestro:tasktype.
  • Label [partial] kind and org labels exist; no free-form labels. Sources: ai-maestro:tasktype.
  • Assign [supported] Primary assignee plus up to 10 owners; project cards forward instructions to the assignee. Sources: ai-maestro:tasksdoc, ai-maestro:tasksvc.
  • Filter [supported] Matrix, Org and Attention views filter by quadrant, org, overdue and waiting. Sources: ai-maestro:tasksdoc.
  • Archive [unsupported] Cards are completed or deleted; no archive state. Sources: ai-maestro:tasktype.
  • Reopen [supported] Status can be moved back from completed. Sources: ai-maestro:tasktype.
  • Project epic views [partial] Agent, team and project boards and an Org view; no epics. Sources: ai-maestro:tasksdoc.
  • Idea parking [supported] `aimaestro-task.sh park` saves an idea card (kind idea) off the board. Sources: ai-maestro:tasksdoc.
  • 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 [partial] Cards are separate from sessions and carry origin ids, but a card does not own sessions. Sources: ai-maestro:tasksdoc.
  • Metadata [supported] Status, due, owners, origin, kind, quadrant, waiting, result, blockers, comments. Sources: ai-maestro:tasktype.
  • Durable states [supported] backlog, pending, in_progress, review, waiting, completed persisted with timestamps. Sources: ai-maestro:tasktype, ai-maestro:taskreg.
  • External tracker requirement [supported] No external tracker is needed. Sources: ai-maestro:taskreg.

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

Sourced 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • 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.
14 atomic answers

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

Agent cross-checked partial

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

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
9 atomic answers

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

Coordination and automation

COORD-01

Parallel work

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
5 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
7 atomic answers
  • 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 [supported] Agents add and assign cards via CLI/API. Sources: ai-maestro:tasksdoc.
  • Claims [partial] Owners list marks shared responsibility; no exclusive claim. Sources: ai-maestro:tasksdoc.
  • Queues [partial] wake-queue and message queues exist for waking agents, not for work. Sources: ai-maestro:tasksvc.
  • Routing [partial] Closed teams route external messages through the chief-of-staff. Sources: ai-maestro:teamtype.
  • Duplicate prevention [partial] Diagnostics warn when two agents share a folder; agents clone separately. Sources: ai-maestro:diag, ai-maestro:concepts.
  • Ownership enforcement [unsupported] Ownership is a convention; nothing prevents two agents from taking the same card. Sources: ai-maestro:taskreg.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
12 atomic answers
  • Roles [supported] AgentRole manager, chief-of-staff, member, plus a manager link and org chart. Sources: ai-maestro:agenttype.
  • 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 [supported] AMP signed messages with priority and types, delivered by Stop hook, channel or typing. Sources: ai-maestro:hook, ai-maestro:channel.
  • Results return [partial] Replies come back as AMP messages; there is no structured result return. Sources: ai-maestro:hook.
  • Cross harness [supported] Claude Code, Codex and Grok agents exchange AMP messages. Sources: ai-maestro:programs.
  • Orchestration owner [supported] Product-owned messaging and agent management skills; no hidden provider subagents. Sources: ai-maestro:plugskills.
  • Activation [supported] Installed with the plugin; messaging on by default. Sources: ai-maestro:readme.
  • Authentication [supported] AMP API keys and Ed25519 signatures; AID identity. Sources: ai-maestro:ampauth.
  • Live progress [partial] Status and chat of any agent are visible; no parent-level child progress view. Sources: ai-maestro:readme.
  • Retained results [supported] Messages persist in the inbox files and transcripts. Sources: ai-maestro:ampauth.
  • Followup [supported] Any agent can be messaged again after finishing. Sources: ai-maestro:readme.
  • Invocation [supported] Natural language ("send a message to backend") through the agent-messaging skill. Sources: ai-maestro:readme.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
8 atomic answers
  • Schedules [supported] Cron expressions with timezone per schedule. Sources: ai-maestro:schedreg.
  • Events [partial] Gateway messages and AMP messages wake agents; no repository event triggers. Sources: ai-maestro:gateways, ai-maestro:hook.
  • Recurring tasks [supported] Morning triage, nightly checks and weekly reports are the documented use. Sources: ai-maestro:readme.
  • Completion conditions [unsupported] No completion conditions on schedules. Sources: ai-maestro:sched.
  • Scheduler location [supported] Runs inside the AI Maestro server on the host (60 s loop). Sources: ai-maestro:sched.
  • Overlaps [supported] A run in flight is skipped. Sources: ai-maestro:agentsched.
  • Retries [partial] Error back-off instead of immediate retry; MAX 50 executions logged. Sources: ai-maestro:agentsched, ai-maestro:schedreg.
  • Client independence [supported] Runs server-side; closing the browser does not stop it, but the host must run. Sources: ai-maestro:sched.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
10 atomic answers
  • Pause [partial] Hibernate stops the session; no mid-turn pause. Sources: ai-maestro:readme.
  • Stop [supported] Hibernate or delete agent; terminal Ctrl+C. Sources: ai-maestro:readme.
  • Resume [supported] Wake resumes the agent (claude --continue style) with history. Sources: ai-maestro:readme.
  • Steer [supported] Chat or terminal at any time. Sources: ai-maestro:chatarch.
  • Notifications [partial] Push to the iPhone app and in-dashboard Needs you; Slack/Discord gateways. Sources: ai-maestro:pushexpo, ai-maestro:gateways.
  • Pending decisions [supported] Questions and approvals appear as cards; Attention page lists them. Sources: ai-maestro:programs.
  • Escalation [partial] Agent-to-human managers and the chief-of-staff role; no timed escalation. Sources: ai-maestro:agenttype.
  • Visible errors [partial] Delivery verification and Doctor checks; some failures only show in the terminal. Sources: ai-maestro:chatarch.
  • 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 [supported] Transcripts, search, export and playback tabs. Sources: ai-maestro:readme.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
8 atomic answers
  • 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 [partial] Manager hierarchy and org view; no parent/child cards. Sources: ai-maestro:agenttype, ai-maestro:tasksdoc.
  • Dependencies [partial] blockedBy on cards; no dependency graph. Sources: ai-maestro:taskreg.
  • Attention [supported] Attention page: overdue, waiting on you and agents needing you. Sources: ai-maestro:tasksdoc.
  • History [partial] Playback and card timestamps; no fleet activity timeline. Sources: ai-maestro:readme.
  • Workload [partial] Matrix counts open cards per agent and host. Sources: ai-maestro:tasksdoc.
  • Navigation errors [unknown] Failed-run navigation is not documented. Sources: ai-maestro:tasksdoc.
  • Fixture mode [unknown] Catalog did not exercise the product. Sources: ai-maestro:readme.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
10 atomic answers
  • Quick task [supported] Chat with an agent or create a card. Sources: ai-maestro:chatarch.
  • Growing epic [unsupported] No epics. Sources: ai-maestro:tasktype.
  • Presets [partial] Wake dialog launch choices and plugin personalities act as presets; none required. Sources: ai-maestro:progchoices.
  • Natural language [supported] Agents are told what to do in plain language, including messaging. Sources: ai-maestro:readme.
  • Agent configuration [supported] Program, model, permission mode, tools profile, avatar and role per agent. Sources: ai-maestro:progchoices.
  • In run changes [partial] Chat steering and card edits; no coordinator re-plan. Sources: ai-maestro:chatarch.
  • Live roles [partial] Team meeting tiles show agents; roles are manager/COS/member. Sources: ai-maestro:teamtype.
  • Retained relationships [partial] Manager links and card origin persist. Sources: ai-maestro:agenttype.
  • Discoverability [supported] Help panel, tutorials and docs. Sources: ai-maestro:readme.
  • Auth friction [partial] Each CLI must be logged in on every host. Sources: ai-maestro:programs.

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

Sourced 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • 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.
12 atomic answers
  • Local [supported] tmux on the host running the dashboard. Sources: ai-maestro:readme.
  • 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 [supported] The whole product is self-hosted; each host runs its own server. Sources: ai-maestro:readme.
  • Managed cloud [unsupported] No vendor-operated cloud ("Not yet"). Sources: ai-maestro:readme.
  • Hybrid [supported] Mixed local, Docker and cloud agents appear in one dashboard. Sources: ai-maestro:readme.
  • Provisioning [supported] Terraform modules provision EC2 and ECS from the dashboard or CLI. Sources: ai-maestro:cloud, ai-maestro:tfreadme.
  • Payer [supported] The user pays their cloud provider and CLI subscriptions. Sources: ai-maestro:readme.
  • Resources [partial] Docker agents default to 2 CPUs and 4g; Linux sizing guide for hosts. Sources: ai-maestro:docker, ai-maestro:readme.
  • 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 [partial] EC2/ECS run until destroyed; Docker restart unless-stopped; no vendor lifetime. Sources: ai-maestro:docker.
  • Client disconnect [supported] tmux sessions persist after the dashboard or browser closes. Sources: ai-maestro:security.
  • Other device continuation [supported] Any browser or the iPhone app can reach the same host. Sources: ai-maestro:concepts, ai-maestro:iphonepage.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
12 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
12 atomic answers
  • Client disconnect [supported] tmux sessions persist after closing the dashboard. Sources: ai-maestro:security.
  • Worker crash [partial] Hibernate/wake and Doctor checks; crashed CLIs need a wake. Sources: ai-maestro:readme.
  • Service restart [supported] Agents are tmux sessions independent of the Node server and are rediscovered. Sources: ai-maestro:concepts.
  • 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 [supported] Chat history reads each CLI transcript files. Sources: ai-maestro:programs.
  • Process reconnect [supported] Terminal re-attaches to tmux. Sources: ai-maestro:concepts.
  • Task resume [supported] Wake continues the agent session. Sources: ai-maestro:programs.
  • State reconstruction [partial] Pending reconcile and chat-state files; Doctor. Sources: ai-maestro:hook.
  • Context loss [partial] Compaction and the 30-day transcript limit are cited. Sources: ai-maestro:ltm.
  • Duplicate actions [partial] Stop-hook dedup of delivered messages; duplicate typing risks are discussed. Sources: ai-maestro:hook, ai-maestro:chatarch.
  • Manual repair [partial] Troubleshooting docs and the Doctor. Sources: ai-maestro:readme.
  • Multi day continuity [supported] Long-term memory and persistent identity target months-long continuity. Sources: ai-maestro:ltm.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
10 atomic answers
  • 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 [unsupported] No cache sharing between agents. Sources: ai-maestro:srch-sandbox.
  • Snapshots [unsupported] No snapshots; agent export/import archives exist. Sources: ai-maestro:srch-sandbox.
  • Services [unsupported] No service orchestration for project dependencies. Sources: ai-maestro:srch-sandbox.
  • Ports [partial] Docker agents are assigned a host port; tmux agents manage their own. Sources: ai-maestro:docker.
  • Secrets [supported] aim-secret injects named secrets into commands. Sources: ai-maestro:secrets.
  • Duplicate installs [partial] Each clone has its own installs; the README recommends partial clones for large repos. Sources: ai-maestro:readme.
  • Collisions [partial] Not handled for tmux agents. Sources: ai-maestro:docker.
  • Remote setup [supported] remote-install.sh and headless mode. Sources: ai-maestro:readme.
  • Automatic repair [partial] Installers repair partially; the Doctor diagnoses. Sources: ai-maestro:readme.

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

Agent cross-checked partial

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

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
8 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
13 atomic answers
  • Logs [partial] Chat transcripts, terminal and server logs; log rotation script. Sources: ai-maestro:programs.
  • Traces [unsupported] No tracing. Sources: ai-maestro:srch-budget.
  • Failure reasons [partial] Errors appear in chat for readers that parse them; Doctor. Sources: ai-maestro:programs.
  • Usage export [partial] Transcript export; no usage export. Sources: ai-maestro:readme.
  • Task stats [unsupported] No per-card statistics. Sources: ai-maestro:tasktype.
  • Agent stats [supported] Sessions, tokens and estimated cost tiles per agent. Sources: ai-maestro:agenttype, ai-maestro:telsvc.
  • Project stats [unsupported] No project statistics. Sources: ai-maestro:tasktype.
  • Time stats [partial] Timestamps on cards; metrics tiles lack time series. Sources: ai-maestro:taskreg.
  • Failure status [partial] Needs-you and offline states; no explicit failed state. Sources: ai-maestro:programs.
  • Approval status [supported] Needs-you status and approval cards. Sources: ai-maestro:programs.
  • 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 [unsupported] No benchmark method; ADEMark does not list this product. Sources: ai-maestro:readme.
  • Responsiveness [unknown] Not measured by this catalog. Sources: ai-maestro:readme.

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
14 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
12 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
11 atomic answers

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

Agent cross-checked partial

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

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
9 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
14 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
11 atomic answers

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

Sourced 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • 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.
13 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
12 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • diffs: No diff artifact.
  • screenshots: Attachments can carry images; no gallery.
  • recordings: No recordings.
  • previews: Canvas pages render in the dashboard.
13 atomic answers

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

Agent cross-checked unsupported

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

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
11 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
9 atomic answers

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

Agent cross-checked partial

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

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • approve: No approval flow.
  • merge: No merge flow.
  • release: None.
  • deploy: Dashboard deploys agents to EC2/ECS, not user code.
6 atomic answers

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

Agent cross-checked partial

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

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
9 atomic answers

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

Agent cross-checked partial

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

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
12 atomic answers

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

Ownership, privacy and economics

Agent cross-checked 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).

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
6 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
8 atomic answers
  • Self hosting [supported] Runs entirely on user hosts, with headless workers. Sources: ai-maestro:readme.
  • 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 [supported] Export agent and transcript export dialogs. Sources: ai-maestro:readme.
  • Import [supported] Import agent dialog and aimaestro-task.sh import. Sources: ai-maestro:tasksdoc.
  • Formats [partial] JSON files and archives. Sources: ai-maestro:schedreg.
  • Cancellation [not-applicable] No account exists to cancel. Sources: ai-maestro:readme.
  • Account independence [supported] No account. Sources: ai-maestro:readme.
  • History portability [partial] Transcripts export; memory graph is CozoDB. Sources: ai-maestro:ltm.

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

Sourced 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • Version check is not documented as controllable.
15 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • included usage: No metered usage.
  • credits: No credits.
  • overages: None.
  • taxes: Tax treatment on the App Store purchase is not stated.
12 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
11 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
8 atomic answers

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

Agent cross-checked partial

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

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
9 atomic answers
  • Iso scope [unknown] No ISO certificate claim found in the repository, SECURITY.md or website. Sources: ai-maestro:security.
  • Iso issuer [unknown] No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
  • Iso validity [unknown] No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
  • Soc2 type [unknown] No SOC 2 report claim found in the repository, SECURITY.md or website. Sources: ai-maestro:security.
  • Soc2 scope [unknown] No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
  • Soc2 period [unknown] No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
  • Report access [unknown] No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
  • Verification date [unknown] No public certification statement or report found in the checked sources. Sources: ai-maestro:security.
  • Evidence status [partial] Public advisories and a security policy exist; no attestations. Sources: ai-maestro:security.

Sources: ai-maestro:security

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • 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.
10 atomic answers

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

Agent cross-checked 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.

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
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • overages: None.
  • compute markup: No markup; user pays cloud directly.
  • model markup: No markup.
  • cancellation: Nothing recurring.
9 atomic answers

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.

Kind
documented
Locator
Quick Start; Features; Agent Deployment; FAQ
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.

Kind
documented
Locator
support matrix table; Grok Build; Codex CLI; Pi; GitHub Copilot CLI; OpenClaw; Anything else
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.

Kind
source-inspected
Locator
manifest()
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.

Kind
source-inspected
Locator
SEND_URL, header comment, COOLDOWN_MS
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.

Kind
documented
Locator
schema.org MobileApplication; "When can I get it?"; Android answer
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.

Kind
documented
Locator
iTunes lookup API id6823011943: trackName, version, minimumOsVersion, releaseDate, price
Source date
2026-11-14
Retrieved
2026-11-16
ai-maestro:reqs

docs/REQUIREMENTS.md

Minimum macOS 12.0, recommended 13, tested on 14+.

Kind
documented
Locator
macOS section; hardware
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.

Kind
documented
Locator
Prerequisites
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.

Kind
documented
Locator
Network Access Configuration; By design no authentication; tmux Session Security; Resolved Advisories
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.

Kind
documented
Locator
Peer Mesh Network; Agents and tmux Sessions; Agent Ownership
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.

Kind
documented
Locator
Users; Capabilities and Constraints
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.

Kind
documented
Locator
What a card holds; For agents: aimaestro-task.sh; API; Commit to session
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.

Kind
source-inspected
Locator
directory listing: aimaestro-agent.sh, aimaestro-task.sh, amp-send.sh, aimaestro-call.sh
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.

Kind
source-inspected
Locator
grep -Ei over app, lib, services, components, package.json for electron, tauri, vsix, jetbrains plugin, vscode extension
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.

Kind
source-inspected
Locator
name, version, license, engines, scripts.dev/headless, dependencies
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.

Kind
source-inspected
Locator
ProgramKind union
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.

Kind
documented
Locator
There are TWO chat paths; Why the SDK path
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.

Kind
source-inspected
Locator
header comment events; supportsStopBlock; isStopHookActive
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).

Kind
source-inspected
Locator
launch flags per program
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.

Kind
source-inspected
Locator
grep -Ei for stripe, license key, paywall, subscription plan
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.

Kind
source-inspected
Locator
grep -rniE "CLAUDE_CONFIG_DIR|multiple accounts|switch account" lib services docs README.md
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.

Kind
source-inspected
Locator
dockerArgs: --cap-drop=ALL, --security-opt no-new-privileges, --cpus, --memory, -v workDir:/workspace
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.

Kind
source-inspected
Locator
checkTerraformAvailable, copyTerraformModule
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.

Kind
documented
Locator
Prerequisites; Quick Start
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.

Kind
source-inspected
Locator
file header
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.

Kind
source-inspected
Locator
WEBHOOKS_FILE, generateSecret
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.

Kind
source-inspected
Locator
KEY_PREFIX_LIVE, API_KEYS_FILE
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.

Kind
source-inspected
Locator
grep -niE "stable|deprecat|breaking|semver|api version" README.md docs/*.md SECURITY.md
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.

Kind
source-inspected
Locator
MODES_BY_KIND, ALL_PERMISSION_MODES
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.

Kind
source-inspected
Locator
Team, TeamType, Meeting
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.

Kind
documented
Locator
Use; Where the value lives
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.

Kind
source-inspected
Locator
directory listing
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.

Kind
documented
Locator
overview
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.

Kind
source-inspected
Locator
TaskStatus, Task, TaskComment
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.

Kind
source-inspected
Locator
resolveTaskDeps, updateScopeTask, wouldCreateScopeCycle
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).

Kind
source-inspected
Locator
CHECK_INTERVAL_MS, startScheduler, runningExecutions
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.

Kind
source-inspected
Locator
grep -Ei for createPullRequest, gh pr create, octokit, /pulls, pull_request
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).

Kind
source-inspected
Locator
sendInstruction, receiveInstruction, assigneeOk
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.

Kind
source-inspected
Locator
file header
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.

Kind
source-inspected
Locator
AgentRole, Agent.metrics, estimatedCost, totalTokensUsed
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.

Kind
documented
Locator
Concepts; consolidation 2 AM; recall
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.

Kind
source-inspected
Locator
getMemory, initializeMemory
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.

Kind
source-inspected
Locator
GET, DELETE ?id=, PATCH handlers
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.

Kind
source-inspected
Locator
deleteMemory; per-memory Delete button
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.

Kind
source-inspected
Locator
grep -Ei for diff2html, react-diff, unified diff, git diff over components and services
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.

Kind
source-inspected
Locator
agentFilter state and cardMatchesAgent
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.

Kind
source-inspected
Locator
writeFileSync at line 71; grep for lock|mutex|etag|expectedVersion
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.

Kind
source-inspected
Locator
ROUTE_RATE_LIMIT_MAX
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.

Kind
source-inspected
Locator
grep -Ei for maxBudget, max-budget, maxTurns, max_turns, spend limit, token limit, timeout per task
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.

Kind
source-inspected
Locator
shared folder check
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.

Kind
source-inspected
Locator
SCHEDULES_FILE, cron-parser, MAX_EXECUTIONS_PER_SCHEDULE
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.

Kind
source-inspected
Locator
inFlight, backoff comment, skipped
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.

Kind
source-inspected
Locator
variable aws_region
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.

Kind
source-inspected
Locator
grep -Ei for sandbox, bubblewrap, seatbelt in services and lib
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.

Kind
source-inspected
Locator
file header
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.

Kind
source-inspected
Locator
metrics.totalTokensUsed, estimatedCost
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).

Kind
source-inspected
Locator
isTelemetryEnabled, claudeTelemetryEnvPrefix
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.

Kind
source-inspected
Locator
grep -Ei for saml, oidc, openid, scim, sso, oauth login, organization roles
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.

Kind
documented
Locator
Status line; Rules; Section 8
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.

Kind
source-inspected
Locator
Keyboard Shortcuts table
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.

Kind
source-inspected
Locator
whole file
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.

Kind
documented
Locator
release notes
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.

Kind
source-inspected
Locator
REMOTE_VERSION_URL
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.

Kind
documented
Locator
stargazers_count, license, pushed_at
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.

Kind
source-inspected
Locator
top entries
Source date
Not stated
Retrieved
2026-11-16
Commit
3acb573466ccf28ed1d044ae85c528320734d220
Path
CHANGELOG.md

Comparisons with AI Maestro

Compare AI Maestro with any other product on adecomparison.com.