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

# Runner: ADE findings

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

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

50 of 51 criteria have a sourced finding; 49 were also cross-checked by a second agent. Source checks: 2026-11-16. A missing sourced finding is not evidence that a capability is absent.

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

## Access and agent choice

### ACC-01: Client access

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

Desktop app for macOS and Windows (Linux beta) plus a runner CLI; remote control from other computers is a private beta and an iPhone app is waitlisted; no browser client or editor extension.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service, Remote access through the hosted relay (private beta) and iPhone beta; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=macOS, Windows, Linux (beta); execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- mobile_apps: iPhone app is in private beta with a waitlist; Android not mentioned.
- browser: No browser client; remote control goes through the desktop app on another computer.
- mobile_browser: No mobile web client documented.
- editor_extensions: No editor extension; Open in editor buttons launch external editors.
- cross_device_continuity: Remote control of another computer sessions via relay is invite-only private beta (mainland China).

- desktop_os — Desktop os [supported]: macOS 12+ (Apple Silicon and Intel), Windows 10 1809+ x64, Linux ARM64 and x86_64 in beta (glibc 2.35+). Sources: runner:install, runner:release.
- mobile_apps — Mobile apps [partial]: iPhone app is in private beta with a waitlist; Android not mentioned. Sources: runner:site.
- browser — Browser [unsupported]: No browser client; remote control goes through the desktop app on another computer. Sources: runner:remote, runner:srch-team.
- mobile_browser — Mobile browser [unsupported]: No mobile web client documented. Sources: runner:remote.
- cli — Cli [supported]: runner CLI controls chats, crews, missions, sessions and messages and works with the app closed. Sources: runner:cli-doc, runner:drive.
- editor_extensions — Editor extensions [unsupported]: No editor extension; Open in editor buttons launch external editors. Sources: runner:chats.
- task_actions — Task actions [supported]: Start chats and missions, answer feed questions, stop/resume/restart slots, review files and diffs, from app or CLI. Sources: runner:missions, runner:cli-doc, runner:chats.
- notifications — Notifications [supported]: Desktop notifications for agent needs-input, finished turn, failure and optional mission events. Sources: runner:readme, runner:chats.
- cross_device_continuity — Cross device continuity [partial]: Remote control of another computer sessions via relay is invite-only private beta (mainland China). Sources: runner:remote.

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

Sources: runner:install, runner:readme, runner:release, runner:site, runner:remote, runner:srch-team, runner:cli-doc, runner:drive, runner:chats, runner:missions

### ACC-02: Agent and model choice

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

Launches separately installed agent CLIs in real terminals: Codex, Claude Code, Antigravity CLI, Copilot CLI, pi, Cursor Agent, Grok Build, OpenCode v2 and opt-in TRAE; custom launch flags and custom role commands.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- model_providers: Models discovered from each CLI; provider choice stays inside the agent CLI.
- custom_adapters: Roles can use a custom command and every agent accepts custom flags; no generic adapter API beyond built-in runtimes (TRAE is opt-in).

- harnesses — Harnesses [supported]: Nine runtimes with per-agent capability table; Claude Code and Codex are primary. Sources: runner:agents-doc.
- model_providers — Model providers [partial]: Models discovered from each CLI; provider choice stays inside the agent CLI. Sources: runner:agents-doc.
- custom_adapters — Custom adapters [partial]: Roles can use a custom command and every agent accepts custom flags; no generic adapter API beyond built-in runtimes (TRAE is opt-in). Sources: runner:agents-doc.
- session_integration — Session integration [supported]: Hosts each CLI in a real PTY and reads state through agent hooks, OSC 7501 terminal status or terminal activity; no embedded harness. Sources: runner:agents-doc, runner:arch.
- mixed_harness_operation — Mixed harness operation [supported]: A crew can mix agents per slot (e.g. Codex coder with Claude Code reviewer). Sources: runner:crews.

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

Sources: runner:agents-doc, runner:readme, runner:arch, runner:crews

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

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

Each agent CLI uses its own login (subscription or API); Runner adds multiple Claude Code accounts and a usage indicator; no vendor credits or Runner-billed models.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- api_accounts: Configured in the agent CLI (pi and OpenCode need a provider configured there).
- vendor_credits: No Runner-provided model credits.
- local_models: Possible through agents that support them (pi, OpenCode); Runner has no model runtime.
- provider_restrictions: Provider terms for driving CLIs are third-party documents not stated in the repository.

- agent_subscriptions — Agent subscriptions [supported]: Agent CLI provides the model connection with its own account; Claude Code, Codex, Copilot subscriptions work through their native sign-in. Sources: runner:install, runner:agents-doc.
- api_accounts — Api accounts [partial]: Configured in the agent CLI (pi and OpenCode need a provider configured there). Sources: runner:agents-doc.
- vendor_credits — Vendor credits [unsupported]: No Runner-provided model credits. Sources: runner:srch-cost.
- local_models — Local models [partial]: Possible through agents that support them (pi, OpenCode); Runner has no model runtime. Sources: runner:agents-doc.
- account_switching — Account switching [supported]: Multiple Claude Code accounts with a Use switcher. Sources: runner:claude-acc.
- vendor_account_requirement — Vendor account requirement [supported]: No Runner account is needed; account sign-in is only for remote access. Sources: runner:remote.
- provider_restrictions — Provider restrictions [unknown]: Provider terms for driving CLIs are third-party documents not stated in the repository.

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

Sources: runner:install, runner:claude-acc, runner:agents-doc, runner:srch-cost, runner:remote

### ACC-04: Onboarding and project prerequisites

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

Download, run first-run Setup to detect or install agent CLIs and sign in, pick a project directory and start a chat or mission; works in any folder; Git panels need a repository; no cloud or VPS installer.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- hosted_git: No GitHub integration; agents handle remotes.
- managed_cloud_setup: No managed cloud execution.
- byo_vps_onboarding: No remote-host installer; remote access reaches only another computer running Runner (private beta).

- first_task_setup — First task setup [supported]: Setup page checks agents, installs npm-packaged CLIs, opens a terminal to sign in and prepares the Pair coding crew. Sources: runner:install.
- no_git — No git [supported]: Missions start in any directory; Files shows a folder tree without git status. Sources: runner:first-mission, runner:chats.
- local_git_without_remote — Local git without remote [supported]: Changes and Files use local git only. Sources: runner:chats.
- hosted_git — Hosted git [unsupported]: No GitHub integration; agents handle remotes. Sources: runner:srch-pr.
- prerequisite_guidance — Prerequisite guidance [supported]: Install guide lists OS versions, Node and Git for Windows needs, signing steps. Sources: runner:install.
- managed_cloud_setup — Managed cloud setup [unsupported]: No managed cloud execution. Sources: runner:remote.
- byo_vps_onboarding — Byo vps onboarding [unsupported]: No remote-host installer; remote access reaches only another computer running Runner (private beta). Sources: runner:remote.

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

Sources: runner:install, runner:first-mission, runner:chats, runner:srch-pr, runner:remote

### ACC-05: Programmable access

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

Full runner CLI over the local daemon socket with JSON output for chats, crews, missions, sessions and messages; no HTTP API, SDK, MCP server or webhooks.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- api: runnerd.sock typed request table used by app and CLI; not a documented public API.
- sdk: No SDK.
- mcp_server: Agents drive Runner through the CLI and an installed skill, not MCP.
- webhooks: No webhooks.
- authentication: Local socket access as the user; remote CLI uses account sign-in and PIN pairing.
- stability: Alpha product; no CLI stability policy found.

- cli — Cli [supported]: runner CLI with project, role, crew, mission, chat, session, msg, remote and daemon command groups. Sources: runner:cli-doc.
- api — Api [partial]: runnerd.sock typed request table used by app and CLI; not a documented public API. Sources: runner:arch, runner:process.
- sdk — Sdk [unsupported]: No SDK. Sources: runner:srch-team.
- mcp_server — Mcp server [unsupported]: Agents drive Runner through the CLI and an installed skill, not MCP. Sources: runner:drive.
- webhooks — Webhooks [unsupported]: No webhooks. Sources: runner:srch-sched.
- operations — Operations [supported]: Create, inspect, stop, resume, restart, message, answer and follow feeds. Sources: runner:cli-doc.
- authentication — Authentication [partial]: Local socket access as the user; remote CLI uses account sign-in and PIN pairing. Sources: runner:process, runner:remote.
- stability — Stability [unknown]: Alpha product; no CLI stability policy found.

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

Sources: runner:cli-doc, runner:drive, runner:arch, runner:process, runner:srch-team, runner:srch-sched, runner:remote

### ACC-06: External tools and extensions

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

Settings manage each agent own MCP servers and skills and install a Runner skill; Runner is not itself an MCP client or server.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- mcp_client: Settings list and toggle MCP servers per agent by editing native config; the agent is the MCP client.
- plugins: No Runner plugin system.
- custom_tools: Custom launch flags and role commands.
- authentication: Inherited from each agent config.
- permission_scope: Toggles change only the touched entry for new sessions.

- mcp_client — Mcp client [partial]: Settings list and toggle MCP servers per agent by editing native config; the agent is the MCP client. Sources: runner:mcp-skills.
- plugins — Plugins [unsupported]: No Runner plugin system. Sources: runner:srch-team.
- custom_tools — Custom tools [partial]: Custom launch flags and role commands. Sources: runner:agents-doc.
- instructions_import — Instructions import [supported]: Skills catalog view and switch per agent; roles and crew conventions supply instructions. Sources: runner:mcp-skills, runner:crews.
- authentication — Authentication [partial]: Inherited from each agent config. Sources: runner:mcp-skills.
- permission_scope — Permission scope [partial]: Toggles change only the touched entry for new sessions. Sources: runner:mcp-skills.
- integration_owner — Integration owner [supported]: Inherited from the underlying agents; Runner edits their config. Sources: runner:mcp-skills.

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

Sources: runner:mcp-skills, runner:drive, runner:srch-team, runner:agents-doc, runner:crews

### ACC-07: Client implementation

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

Native Rust app using GPUI with alacritty_terminal; no Electron or Tauri.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- mobile_implementation: iPhone beta is private; implementation not public.
- hybrids: No web hybrid in the public repository.

- desktop_implementation — Desktop implementation [supported]: Rust GPUI UI on a GPU-drawn alacritty_terminal grid, with runnerd daemon. Sources: runner:readme, runner:arch.
- mobile_implementation — Mobile implementation [unknown]: iPhone beta is private; implementation not public. Sources: runner:site.
- hybrids — Hybrids [unsupported]: No web hybrid in the public repository. Sources: runner:cargo.
- implementation_evidence — Implementation evidence [supported]: Workspace crates and README acknowledgements. Sources: runner:cargo, runner:readme.

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

Sources: runner:readme, runner:cargo, runner:arch, runner:site

## Planning and context

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

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

Work starts from a typed goal in a mission or chat; no tracker, import or sync.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- local_creation: A mission with a goal is the closest entity; no task record.
- external_import: No tracker import.
- chat_git_triggers: No chat or git triggers.
- authoritative_tracker: No tracker.
- stable_ids: Missions and sessions have IDs (ULIDs) usable in CLI.
- sync: No sync.
- supported_edits: No tracker edits.
- external_roundtrips: Not applicable without a tracker.

- local_creation — Local creation [partial]: A mission with a goal is the closest entity; no task record. Sources: runner:missions.
- prompt_intake — Prompt intake [supported]: Goal typed in the launcher or passed via --goal-file. Sources: runner:missions, runner:cli-doc.
- external_import — External import [unsupported]: No tracker import. Sources: runner:srch-issue.
- chat_git_triggers — Chat git triggers [unsupported]: No chat or git triggers. Sources: runner:srch-sched.
- authoritative_tracker — Authoritative tracker [unsupported]: No tracker. Sources: runner:srch-issue.
- stable_ids — Stable ids [partial]: Missions and sessions have IDs (ULIDs) usable in CLI. Sources: runner:drive.
- sync — Sync [unsupported]: No sync. Sources: runner:srch-issue.
- supported_edits — Supported edits [unsupported]: No tracker edits. Sources: runner:srch-issue.
- external_roundtrips — External roundtrips [unsupported]: Not applicable without a tracker. Sources: runner:srch-issue.

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

Sources: runner:missions, runner:srch-issue, runner:cli-doc, runner:srch-sched, runner:drive

### PLAN-02: Durable task plans

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

No plan object; missions have a goal and crews have team conventions.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- plans: No plan entity.
- acceptance_criteria: No acceptance criteria field; goals describe validation.
- editors: Roles and crews are editable; goals are text.
- revisions: No revision history.
- implementation_links: No links to implementation.
- amendment: Message members mid-run through the feed.

- plans — Plans [unsupported]: No plan entity. Sources: runner:srch-issue.
- acceptance_criteria — Acceptance criteria [unsupported]: No acceptance criteria field; goals describe validation. Sources: runner:drive.
- editors — Editors [partial]: Roles and crews are editable; goals are text. Sources: runner:crews.
- revisions — Revisions [unsupported]: No revision history. Sources: runner:srch-issue.
- implementation_links — Implementation links [unsupported]: No links to implementation. Sources: runner:srch-issue.
- amendment — Amendment [partial]: Message members mid-run through the feed. Sources: runner:missions.
- restart_persistence — Restart persistence [supported]: Mission feed and sessions persist across restarts. Sources: runner:process, runner:missions.

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

Sources: runner:missions, runner:crews, runner:srch-issue, runner:drive, runner:process

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

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

No epics, dependencies or task hierarchy; handoff order is defined in role prompts and team conventions.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- epics: No such feature (bounded search); crew slots are roles, not work items.
- hierarchy: No such feature (bounded search); crew slots are roles, not work items.
- blockers: No such feature (bounded search); crew slots are roles, not work items.
- readiness: No such feature (bounded search); crew slots are roles, not work items.
- enforcement: No such feature (bounded search); crew slots are roles, not work items.
- state_propagation: No such feature (bounded search); crew slots are roles, not work items.
- task_to_epic: No such feature (bounded search); crew slots are roles, not work items.
- identity_retention: No such feature (bounded search); crew slots are roles, not work items.
- workflow_constraints: Crew conventions say who acts first; no rigid workflow engine.

- epics — Epics [unsupported]: No such feature (bounded search); crew slots are roles, not work items. Sources: runner:srch-issue.
- hierarchy — Hierarchy [unsupported]: No such feature (bounded search); crew slots are roles, not work items. Sources: runner:srch-issue.
- blockers — Blockers [unsupported]: No such feature (bounded search); crew slots are roles, not work items. Sources: runner:srch-issue.
- readiness — Readiness [unsupported]: No such feature (bounded search); crew slots are roles, not work items. Sources: runner:srch-issue.
- enforcement — Enforcement [unsupported]: No such feature (bounded search); crew slots are roles, not work items. Sources: runner:srch-issue.
- state_propagation — State propagation [unsupported]: No such feature (bounded search); crew slots are roles, not work items. Sources: runner:srch-issue.
- task_to_epic — Task to epic [unsupported]: No such feature (bounded search); crew slots are roles, not work items. Sources: runner:srch-issue.
- identity_retention — Identity retention [unsupported]: No such feature (bounded search); crew slots are roles, not work items. Sources: runner:srch-issue.
- workflow_constraints — Workflow constraints [partial]: Crew conventions say who acts first; no rigid workflow engine. Sources: runner:crews.

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

Sources: runner:crews, runner:srch-issue

### PLAN-04: Shared context and memory

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

Roles and crew conventions, skills catalog and Runner skill; no managed memory or project docs store.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- project_docs: Files view reads docs; none stored.
- memory: No managed memory.
- scope: Per project, per crew, per agent.
- provenance: None.
- correction: None.
- deletion: None.
- freshness: None.
- takeover_continuity: Mission feed and resumable sessions persist; single user.

- instructions — Instructions [supported]: Role instructions and team conventions delivered to every member. Sources: runner:crews, runner:missions.
- skills — Skills [supported]: Skills catalog and switch per agent; Runner skill installed. Sources: runner:mcp-skills, runner:drive.
- project_docs — Project docs [partial]: Files view reads docs; none stored. Sources: runner:chats.
- memory — Memory [unsupported]: No managed memory. Sources: runner:srch-issue.
- scope — Scope [partial]: Per project, per crew, per agent. Sources: runner:crews.
- provenance — Provenance [unsupported]: None. Sources: runner:srch-issue.
- correction — Correction [unsupported]: None. Sources: runner:srch-issue.
- deletion — Deletion [unsupported]: None. Sources: runner:srch-issue.
- freshness — Freshness [unsupported]: None. Sources: runner:srch-issue.
- takeover_continuity — Takeover continuity [partial]: Mission feed and resumable sessions persist; single user. Sources: runner:missions.

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

Sources: runner:crews, runner:mcp-skills, runner:missions, runner:drive, runner:chats, runner:srch-issue

### PLAN-05: Architecture and API awareness

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

No indexing or retrieval; Files view with finder, highlighted code and read-only previews beside agents.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- code_search: File finder (⇧⌘O) and command palette; no code search engine.
- indexing: No such feature (bounded search).
- external_knowledge: No such feature (bounded search).
- multimodal_inputs: Not established.
- freshness: No such feature (bounded search).
- access_scope: Files view limited to the session checkout or chosen folder.
- api_retrieval: No such feature (bounded search).
- citations: No such feature (bounded search).
- conflict_detection: No such feature (bounded search).
- review_enforcement: No such feature (bounded search).

- code_search — Code search [partial]: File finder (⇧⌘O) and command palette; no code search engine. Sources: runner:chats.
- indexing — Indexing [unsupported]: No such feature (bounded search). Sources: runner:srch-issue.
- external_knowledge — External knowledge [unsupported]: No such feature (bounded search). Sources: runner:srch-issue.
- multimodal_inputs — Multimodal inputs [unknown]: Not established.
- freshness — Freshness [unsupported]: No such feature (bounded search). Sources: runner:srch-issue.
- access_scope — Access scope [partial]: Files view limited to the session checkout or chosen folder. Sources: runner:chats.
- api_retrieval — Api retrieval [unsupported]: No such feature (bounded search). Sources: runner:srch-issue.
- citations — Citations [unsupported]: No such feature (bounded search). Sources: runner:srch-issue.
- conflict_detection — Conflict detection [unsupported]: No such feature (bounded search). Sources: runner:srch-issue.
- review_enforcement — Review enforcement [unsupported]: No such feature (bounded search). Sources: runner:srch-issue.

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

Sources: runner:chats, runner:srch-issue

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

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

No issue management; missions and chats are pinned, moved, archived and grouped under projects.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- create: No issue or backlog feature (bounded search).
- edit: No issue or backlog feature (bounded search).
- discuss: No issue or backlog feature (bounded search).
- prioritize: No issue or backlog feature (bounded search).
- label: No issue or backlog feature (bounded search).
- assign: No issue or backlog feature (bounded search).
- search: Command palette and sidebar search over chats and missions.
- filter: No issue or backlog feature (bounded search).
- reopen: No issue or backlog feature (bounded search).
- project_epic_views: Projects group chats and missions by directory.
- idea_parking: No issue or backlog feature (bounded search).
- explicit_dispatch: No issue or backlog feature (bounded search).
- task_session_separation: No issue or backlog feature (bounded search).
- metadata: No issue or backlog feature (bounded search).
- durable_states: Mission state and status persisted; not issue states.
- external_tracker_requirement: No issue or backlog feature (bounded search).

- create — Create [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- edit — Edit [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- discuss — Discuss [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- prioritize — Prioritize [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- label — Label [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- assign — Assign [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- search — Search [partial]: Command palette and sidebar search over chats and missions. Sources: runner:chats.
- filter — Filter [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- archive — Archive [supported]: Missions archive and restore. Sources: runner:missions.
- reopen — Reopen [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- project_epic_views — Project epic views [partial]: Projects group chats and missions by directory. Sources: runner:chats.
- idea_parking — Idea parking [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- explicit_dispatch — Explicit dispatch [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- task_session_separation — Task session separation [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- metadata — Metadata [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.
- durable_states — Durable states [partial]: Mission state and status persisted; not issue states. Sources: runner:missions.
- external_tracker_requirement — External tracker requirement [unsupported]: No issue or backlog feature (bounded search). Sources: runner:srch-issue.

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

Sources: runner:missions, runner:srch-issue, runner:chats

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

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

Agents operate missions through the runner CLI, not issues: start, follow, message, answer and read feed; no claims or dependencies.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- shared_ids: Mission and session IDs shared by app and CLI.
- update: Rename, move, link missions.
- claim: No work-item operations.
- assign: No work-item operations.
- dependencies: No work-item operations.
- children: No work-item operations.
- attribution: Feed messages attributed to roster handles.
- permissions: No work-item operations.
- conflicts: No work-item operations.

- shared_ids — Shared ids [partial]: Mission and session IDs shared by app and CLI. Sources: runner:drive.
- read — Read [supported]: runner mission show/feed. Sources: runner:cli-doc.
- create — Create [supported]: runner mission start from an agent. Sources: runner:drive.
- update — Update [partial]: Rename, move, link missions. Sources: runner:cli-doc.
- claim — Claim [unsupported]: No work-item operations. Sources: runner:srch-issue.
- assign — Assign [unsupported]: No work-item operations. Sources: runner:srch-issue.
- state_changes — State changes [supported]: Stop, resume, archive. Sources: runner:cli-doc.
- dependencies — Dependencies [unsupported]: No work-item operations. Sources: runner:srch-issue.
- children — Children [unsupported]: No work-item operations. Sources: runner:srch-issue.
- results — Results [supported]: Reports back to the linked chat. Sources: runner:missions.
- human_visibility — Human visibility [supported]: Same missions visible in app. Sources: runner:missions.
- attribution — Attribution [partial]: Feed messages attributed to roster handles. Sources: runner:missions.
- permissions — Permissions [unsupported]: No work-item operations. Sources: runner:srch-issue.
- conflicts — Conflicts [unsupported]: No work-item operations. Sources: runner:srch-issue.

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

Sources: runner:drive, runner:cli-doc, runner:srch-issue, runner:missions

### PLAN-08: Living product specifications

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

No living specification feature.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- persistent_requirements: No spec store (bounded search).
- human_edits: No spec store (bounded search).
- agent_edits: No spec store (bounded search).
- revisions: No spec store (bounded search).
- approvals: No spec store (bounded search).
- implementation_links: No spec store (bounded search).
- later_retrieval: No spec store (bounded search).
- drift_detection: No spec store (bounded search).
- review_integration: No spec store (bounded search).

- persistent_requirements — Persistent requirements [unsupported]: No spec store (bounded search). Sources: runner:srch-issue.
- human_edits — Human edits [unsupported]: No spec store (bounded search). Sources: runner:srch-issue.
- agent_edits — Agent edits [unsupported]: No spec store (bounded search). Sources: runner:srch-issue.
- revisions — Revisions [unsupported]: No spec store (bounded search). Sources: runner:srch-issue.
- approvals — Approvals [unsupported]: No spec store (bounded search). Sources: runner:srch-issue.
- implementation_links — Implementation links [unsupported]: No spec store (bounded search). Sources: runner:srch-issue.
- later_retrieval — Later retrieval [unsupported]: No spec store (bounded search). Sources: runner:srch-issue.
- drift_detection — Drift detection [unsupported]: No spec store (bounded search). Sources: runner:srch-issue.
- review_integration — Review integration [unsupported]: No spec store (bounded search). Sources: runner:srch-issue.

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

Sources: runner:srch-issue

## Coordination and automation

### COORD-01: Parallel work

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

Many sessions, tabs and missions run concurrently under runnerd; split panes and a sidebar show working, idle and needs-you states; no documented cap.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- quotas: No quota documented or found.
- observed_concurrency: No benchmark published; ADEMark does not list Runner.

- concurrent_sessions — Concurrent sessions [supported]: Every chat and mission member is its own PTY session; split tabs support many panes. Sources: runner:sessions, runner:readme.
- concurrent_tasks — Concurrent tasks [supported]: Several missions can run at once. Sources: runner:missions.
- quotas — Quotas [unsupported]: No quota documented or found. Sources: runner:srch-limits.
- observed_concurrency — Observed concurrency [unknown]: No benchmark published; ADEMark does not list Runner.
- status_visibility — Status visibility [supported]: Working/idle/needs-you indicators, mission states and unread dots in the sidebar. Sources: runner:sessions, runner:missions.

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

Sources: runner:sessions, runner:process, runner:missions, runner:readme, runner:srch-limits

### COORD-02: Ownership and dispatch

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

Crew slots assign roles to agents; messages route by handle; no claims or queues.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- human_assignment: No assignment to humans.
- claims: No claims.
- queues: No queue.
- duplicate_prevention: No duplicate-work prevention; goal text must avoid overlapping edits.
- ownership_enforcement: No enforcement.

- human_assignment — Human assignment [unsupported]: No assignment to humans. Sources: runner:srch-team.
- agent_assignment — Agent assignment [supported]: Slots bind roles/agents; goal and conventions say who acts. Sources: runner:crews.
- claims — Claims [unsupported]: No claims. Sources: runner:srch-issue.
- queues — Queues [unsupported]: No queue. Sources: runner:srch-issue.
- routing — Routing [supported]: Handle addressing and @mentions deliver inbox notices to recipients. Sources: runner:missions.
- duplicate_prevention — Duplicate prevention [unsupported]: No duplicate-work prevention; goal text must avoid overlapping edits. Sources: runner:build-crew.
- ownership_enforcement — Ownership enforcement [unsupported]: No enforcement. Sources: runner:build-crew.

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

Sources: runner:crews, runner:missions, runner:srch-team, runner:srch-issue, runner:build-crew

### COORD-03: Inspectable delegation and communication

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

Mission members message each other by handle through an inbox in a persistent feed; an agent in a chat can delegate to a crew via the runner CLI skill and receives reports; per-slot agent/model/effort.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

- roles — Roles [supported]: Role templates and slot handles (coder, reviewer). Sources: runner:crews.
- model_harness_effort — Model harness effort [supported]: Per-slot agent, model, effort and Codex speed overrides. Sources: runner:crews.
- messages — Messages [supported]: Targeted and broadcast messages, questions to the human. Sources: runner:missions.
- results_return — Results return [supported]: Handoffs in the feed and state reports to the linked chat. Sources: runner:missions.
- cross_harness — Cross harness [supported]: Slots can use different agents. Sources: runner:crews.
- orchestration_owner — Orchestration owner [supported]: Product orchestration: daemon delivers inbox notices and reports; coordinator role can be a third-party agent using the shipped skill. Sources: runner:drive, runner:missions.
- activation — Activation [supported]: Always available; skill toggle in Settings → General → Command line. Sources: runner:drive.
- authentication — Authentication [supported]: Local socket; agents use their own accounts. Sources: runner:process.
- live_progress — Live progress [supported]: Live terminals per member and the feed. Sources: runner:missions.
- retained_results — Retained results [supported]: Feed persists in an event log; archived missions keep their feed. Sources: runner:missions, runner:arch.
- followup — Followup [supported]: Resume stopped sessions and send follow-up messages after completion. Sources: runner:missions.
- invocation — Invocation [supported]: runner mission start from chat or shell. Sources: runner:drive.

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

Sources: runner:missions, runner:drive, runner:crews, runner:process, runner:arch

### COORD-04: Unattended triggers

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

No schedules or event triggers.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- schedules: No scheduler or trigger code (bounded search).
- events: No scheduler or trigger code (bounded search).
- recurring_tasks: No scheduler or trigger code (bounded search).
- completion_conditions: No scheduler or trigger code (bounded search).
- scheduler_location: No scheduler or trigger code (bounded search).
- overlaps: No scheduler or trigger code (bounded search).
- retries: No scheduler or trigger code (bounded search).
- client_independence: No scheduler or trigger code (bounded search).

- schedules — Schedules [unsupported]: No scheduler or trigger code (bounded search). Sources: runner:srch-sched.
- events — Events [unsupported]: No scheduler or trigger code (bounded search). Sources: runner:srch-sched.
- recurring_tasks — Recurring tasks [unsupported]: No scheduler or trigger code (bounded search). Sources: runner:srch-sched.
- completion_conditions — Completion conditions [unsupported]: No scheduler or trigger code (bounded search). Sources: runner:srch-sched.
- scheduler_location — Scheduler location [unsupported]: No scheduler or trigger code (bounded search). Sources: runner:srch-sched.
- overlaps — Overlaps [unsupported]: No scheduler or trigger code (bounded search). Sources: runner:srch-sched.
- retries — Retries [unsupported]: No scheduler or trigger code (bounded search). Sources: runner:srch-sched.
- client_independence — Client independence [unsupported]: No scheduler or trigger code (bounded search). Sources: runner:srch-sched.

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

Sources: runner:srch-sched

### COORD-05: Intervention and attention

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

Stop, resume and restart per slot or mission; steer by messages or typing in terminals; needs-you reports and desktop notifications; interrupted state after restarts.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- pause: Stop halts a slot; no pause that preserves the process.
- escalation: Agents ask the human via the feed.

- pause — Pause [partial]: Stop halts a slot; no pause that preserves the process. Sources: runner:missions.
- stop — Stop [supported]: Stop slot or mission; history kept; repository changes never reverted. Sources: runner:missions.
- resume — Resume [supported]: Resume saved conversations; Restart starts fresh. Sources: runner:missions.
- steer — Steer [supported]: Feed messages and direct terminal input. Sources: runner:missions.
- notifications — Notifications [supported]: Desktop notifications, unread dots, linked-chat reports. Sources: runner:chats, runner:missions.
- pending_decisions — Pending decisions [supported]: Questions on feed cards; Needs you state. Sources: runner:missions.
- escalation — Escalation [partial]: Agents ask the human via the feed. Sources: runner:missions.
- visible_errors — Visible errors [supported]: Failed and Interrupted mission states and per-slot errors. Sources: runner:missions.
- chat_terminal_parity — Chat terminal parity [supported]: Chats are terminals; the same indicators apply. Sources: runner:sessions.
- retained_history — Retained history [supported]: Feed persistent log. Sources: runner:missions, runner:arch.

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

Sources: runner:missions, runner:sessions, runner:chats, runner:arch

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

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

Sidebar tree of projects, chats and missions with per-item state and unread markers; no board of epics or dependencies.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- fleet_fixture: No demo fleet; docs show screenshots.
- parent_child: Missions group under the chat that started them.
- dependencies: None.
- history: Feeds and archived missions.
- workload: Usage indicator for plan limits.
- navigation_errors: Command palette and sidebar navigation.
- fixture_mode: Not established.

- fleet_fixture — Fleet fixture [unknown]: No demo fleet; docs show screenshots.
- parent_child — Parent child [partial]: Missions group under the chat that started them. Sources: runner:missions.
- dependencies — Dependencies [unsupported]: None. Sources: runner:srch-issue.
- attention — Attention [supported]: Needs you / Failed / Interrupted states and notifications. Sources: runner:missions.
- history — History [partial]: Feeds and archived missions. Sources: runner:missions.
- workload — Workload [partial]: Usage indicator for plan limits. Sources: runner:arch.
- navigation_errors — Navigation errors [partial]: Command palette and sidebar navigation. Sources: runner:chats.
- fixture_mode — Fixture mode [unknown]: Not established.

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

Sources: runner:missions, runner:chats, runner:srch-issue, runner:arch

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

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

Crews are reusable presets with per-slot configuration; missions can start empty and add roles; configuration is by role prompts, not a natural-language builder.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- growing_epic: Empty missions can add or remove members while running.
- natural_language: Role instructions are free text.
- retained_relationships: Roster captured in the mission.
- auth_friction: Needs each agent signed in.

- quick_task — Quick task [supported]: A chat or one-line mission. Sources: runner:missions.
- growing_epic — Growing epic [partial]: Empty missions can add or remove members while running. Sources: runner:missions.
- presets — Presets [supported]: Saved crews and the Pair coding starter crew. Sources: runner:crews.
- natural_language — Natural language [partial]: Role instructions are free text. Sources: runner:crews.
- agent_configuration — Agent configuration [supported]: Per-slot agent/model/effort. Sources: runner:crews.
- in_run_changes — In run changes [supported]: Add/remove role mid-mission; change messages. Sources: runner:missions.
- live_roles — Live roles [supported]: Roster and session cards show roles. Sources: runner:missions.
- retained_relationships — Retained relationships [partial]: Roster captured in the mission. Sources: runner:missions.
- discoverability — Discoverability [supported]: Launcher, palette and docs. Sources: runner:missions.
- auth_friction — Auth friction [partial]: Needs each agent signed in. Sources: runner:install.

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

Sources: runner:crews, runner:missions, runner:install

## Execution and reliability

### RUN-01: Laptop-independent execution

Verification status: Sourced (sourced)
Support: partial

Local execution on the user computer; sessions live in runnerd and survive app quit; runnerd and the CLI can also run on a Linux host reached over SSH (optional systemd user service) though no guide presents server execution; remote control of another computer is an invite-only private beta; no vendor cloud.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=local; region=not specified; harness=not specified.

Limitations:
- byo_remote: Docs describe the Linux runnerd systemd user service and using the CLI over SSH, so the daemon can run on a user-controlled host; remote and server execution is not presented as a supported workflow and relay-based remote access is private beta.
- self_hosted: The relay service is Runner hosted and closed.
- managed_cloud: No managed cloud execution.
- hybrid: Control another computer from this one via relay (beta).
- provisioning: None.
- region: Remote access currently available only in mainland China.
- expiry: No expiry.
- other_device_continuation: Another computer can attach via the private-beta relay.

- local — Local [supported]: Sessions run in runnerd on the user machine. Sources: runner:arch, runner:process.
- byo_remote — Byo remote [partial]: Docs describe the Linux runnerd systemd user service and using the CLI over SSH, so the daemon can run on a user-controlled host; remote and server execution is not presented as a supported workflow and relay-based remote access is private beta. Sources: runner:remote, runner:linux-service.
- self_hosted — Self hosted [unsupported]: The relay service is Runner hosted and closed. Sources: runner:remote.
- managed_cloud — Managed cloud [unsupported]: No managed cloud execution. Sources: runner:remote, runner:srch-team.
- hybrid — Hybrid [partial]: Control another computer from this one via relay (beta). Sources: runner:remote.
- provisioning — Provisioning [unsupported]: None. Sources: runner:remote.
- payer — Payer [supported]: User machine and agent subscriptions. Sources: runner:install.
- resources — Resources [supported]: Host machine resources. Sources: runner:install.
- region — Region [partial]: Remote access currently available only in mainland China. Sources: runner:remote.
- expiry — Expiry [unsupported]: No expiry. Sources: runner:process.
- client_disconnect — Client disconnect [supported]: Quit or crash of the app leaves daemon sessions running; reopen to the same terminals. Sources: runner:process, runner:readme.
- other_device_continuation — Other device continuation [partial]: Another computer can attach via the private-beta relay. Sources: runner:remote.

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

Sources: runner:arch, runner:remote, runner:install, runner:process, runner:srch-team, runner:readme, runner:linux-service

### RUN-02: Workspace and process isolation

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

Members share the given directory; Runner creates no branches, worktrees or copies; Files can switch between existing worktrees; no container, VM or OS sandbox of its own.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- branch: Does not create branches; default crew conventions suggest a feature branch.
- worktree: Docs state Runner does not isolate with worktrees; user must create one before launch.
- container: None.
- vm: None.
- os_sandbox: Missions use agent bypass/broad-access modes.
- filesystem: No filesystem boundary; agents run as the user.
- process: Separate PTY per session.
- network: None.
- secrets: Relay uses PIN-based pairing and OS-stored keys; agent secrets stay in agent configs.
- code_separation: Shared directory.
- security_boundary: No containment claim; docs advise trusted folders.

- checkout — Checkout [supported]: Shared working directory per mission. Sources: runner:missions.
- branch — Branch [unsupported]: Does not create branches; default crew conventions suggest a feature branch. Sources: runner:missions, runner:crews.
- worktree — Worktree [unsupported]: Docs state Runner does not isolate with worktrees; user must create one before launch. Sources: runner:build-crew, runner:first-mission.
- container — Container [unsupported]: None. Sources: runner:srch-team.
- vm — Vm [unsupported]: None. Sources: runner:srch-team.
- os_sandbox — Os sandbox [unsupported]: Missions use agent bypass/broad-access modes. Sources: runner:missions, runner:agents-doc.
- filesystem — Filesystem [unsupported]: No filesystem boundary; agents run as the user. Sources: runner:missions.
- process — Process [partial]: Separate PTY per session. Sources: runner:sessions.
- network — Network [unsupported]: None. Sources: runner:missions.
- secrets — Secrets [partial]: Relay uses PIN-based pairing and OS-stored keys; agent secrets stay in agent configs. Sources: runner:remote.
- code_separation — Code separation [unsupported]: Shared directory. Sources: runner:missions.
- security_boundary — Security boundary [unsupported]: No containment claim; docs advise trusted folders. Sources: runner:agents-doc.

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

Sources: runner:missions, runner:build-crew, runner:first-mission, runner:crews, runner:srch-team, runner:agents-doc, runner:sessions, runner:remote

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

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

runnerd keeps sessions alive across app quit or crash; stopped agents resume their conversations; interrupted missions are flagged after a daemon restart; a daemon crash ends PTYs.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- worker_crash: Session crash marks it stopped; daemon crash closes PTYs on macOS and kills sessions.
- expiry: None.
- state_reconstruction: Interrupted state recorded; chat reports on restart.
- context_loss: Interrupted turn is lost; conversation resume depends on the agent.
- duplicate_actions: Not stated.
- manual_repair: Daemon troubleshooting in docs; use Resume/Restart.
- multi_day_continuity: Sessions persist while the machine runs; resume after restart.

- client_disconnect — Client disconnect [supported]: App quit/crash leaves sessions running. Sources: runner:process.
- worker_crash — Worker crash [partial]: Session crash marks it stopped; daemon crash closes PTYs on macOS and kills sessions. Sources: runner:process, runner:arch.
- service_restart — Service restart [supported]: Members resume at next start; mission shows Interrupted when a turn was lost. Sources: runner:missions.
- expiry — Expiry [unsupported]: None. Sources: runner:process.
- transcript_reload — Transcript reload [supported]: Feed event log and agent conversations resume. Sources: runner:missions, runner:arch.
- process_reconnect — Process reconnect [supported]: Reopen the app to the same live terminals. Sources: runner:readme.
- task_resume — Task resume [supported]: Resume saved conversation per session where supported. Sources: runner:agents-doc, runner:missions.
- state_reconstruction — State reconstruction [partial]: Interrupted state recorded; chat reports on restart. Sources: runner:missions.
- context_loss — Context loss [partial]: Interrupted turn is lost; conversation resume depends on the agent. Sources: runner:missions, runner:agents-doc.
- duplicate_actions — Duplicate actions [unknown]: Not stated.
- manual_repair — Manual repair [partial]: Daemon troubleshooting in docs; use Resume/Restart. Sources: runner:missions.
- multi_day_continuity — Multi day continuity [partial]: Sessions persist while the machine runs; resume after restart. Sources: runner:process.

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

Sources: runner:process, runner:missions, runner:arch, runner:readme, runner:agents-doc

### RUN-04: Development environment reliability

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

No dependency, cache, service or port management; terminals show what agents do.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- dependencies: No environment management (bounded search).
- caches: No environment management (bounded search).
- snapshots: No environment management (bounded search).
- services: No environment management (bounded search).
- ports: No environment management (bounded search).
- secrets: No environment management (bounded search).
- duplicate_installs: No environment management (bounded search).
- collisions: No environment management (bounded search).
- remote_setup: No environment management (bounded search).
- automatic_repair: No environment management (bounded search).

- dependencies — Dependencies [unsupported]: No environment management (bounded search). Sources: runner:srch-issue.
- caches — Caches [unsupported]: No environment management (bounded search). Sources: runner:srch-issue.
- snapshots — Snapshots [unsupported]: No environment management (bounded search). Sources: runner:srch-issue.
- services — Services [unsupported]: No environment management (bounded search). Sources: runner:srch-issue.
- ports — Ports [unsupported]: No environment management (bounded search). Sources: runner:srch-issue.
- secrets — Secrets [unsupported]: No environment management (bounded search). Sources: runner:srch-issue.
- duplicate_installs — Duplicate installs [unsupported]: No environment management (bounded search). Sources: runner:srch-issue.
- collisions — Collisions [unsupported]: No environment management (bounded search). Sources: runner:srch-issue.
- remote_setup — Remote setup [unsupported]: No environment management (bounded search). Sources: runner:srch-issue.
- automatic_repair — Automatic repair [unsupported]: No environment management (bounded search). Sources: runner:srch-issue.

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

Sources: runner:chats, runner:srch-issue

### RUN-05: Limits and failure handling

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

No agent time, turn, token or spend limits are enforced; usage indicator shows provider plan-limit percentages.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- time_limits: No limit enforcement (bounded search).
- turn_limits: No limit enforcement (bounded search).
- token_limits: No limit enforcement (bounded search).
- spend_limits: No limit enforcement (bounded search).
- timeouts: Only operational timeouts for Runner internals.
- retries: No limit enforcement (bounded search).
- provider_failures: No limit enforcement (bounded search).
- enforcement: Plan limits are shown, not enforced.

- time_limits — Time limits [unsupported]: No limit enforcement (bounded search). Sources: runner:srch-limits.
- turn_limits — Turn limits [unsupported]: No limit enforcement (bounded search). Sources: runner:srch-limits.
- token_limits — Token limits [unsupported]: No limit enforcement (bounded search). Sources: runner:srch-limits.
- spend_limits — Spend limits [unsupported]: No limit enforcement (bounded search). Sources: runner:srch-limits.
- timeouts — Timeouts [partial]: Only operational timeouts for Runner internals. Sources: runner:srch-limits.
- retries — Retries [unsupported]: No limit enforcement (bounded search). Sources: runner:srch-limits.
- provider_failures — Provider failures [unsupported]: No limit enforcement (bounded search). Sources: runner:srch-limits.
- enforcement — Enforcement [unsupported]: Plan limits are shown, not enforced. Sources: runner:arch.

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

Sources: runner:srch-limits, runner:arch

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

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

Terminal scrollback, mission feed event log, session states and usage-limit indicators; no traces or cost statistics.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- traces: None.
- failure_reasons: Failed/Interrupted states and per-session errors.
- usage_export: None found.
- task_stats: None.
- agent_stats: Per-agent plan usage indicator.
- project_stats: None.
- time_stats: Weekly and 5-hour windows.
- reconnect_consistency: Hook-based state with bridge authority; interrupted marking.
- performance_method: No benchmarks; ADEMark does not list Runner.
- responsiveness: No figures.

- logs — Logs [supported]: runnerd log folder and feed event log. Sources: runner:arch.
- traces — Traces [unsupported]: None. Sources: runner:srch-tele.
- failure_reasons — Failure reasons [partial]: Failed/Interrupted states and per-session errors. Sources: runner:missions.
- usage_export — Usage export [unsupported]: None found. Sources: runner:srch-cost.
- task_stats — Task stats [unsupported]: None. Sources: runner:srch-cost.
- agent_stats — Agent stats [partial]: Per-agent plan usage indicator. Sources: runner:arch.
- project_stats — Project stats [unsupported]: None. Sources: runner:srch-cost.
- time_stats — Time stats [partial]: Weekly and 5-hour windows. Sources: runner:claude-acc.
- failure_status — Failure status [supported]: Failed state. Sources: runner:missions.
- approval_status — Approval status [supported]: Needs you with approval waits. Sources: runner:agents-doc.
- reconnect_consistency — Reconnect consistency [partial]: Hook-based state with bridge authority; interrupted marking. Sources: runner:agents-doc, runner:missions.
- performance_method — Performance method [unknown]: No benchmarks; ADEMark does not list Runner.
- responsiveness — Responsiveness [unknown]: No figures.

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

Sources: runner:arch, runner:missions, runner:sessions, runner:srch-tele, runner:srch-cost, runner:claude-acc, runner:agents-doc

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

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

No dollar cost or token accounting; plan-limit usage percentages for Claude Code, Codex and Antigravity CLI.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- task_cost: No cost accounting (bounded search).
- session_cost: No cost accounting (bounded search).
- child_cost: No cost accounting (bounded search).
- epic_cost: No cost accounting (bounded search).
- harness_aggregation: No aggregation across harnesses.
- billed_vs_estimated: No cost accounting (bounded search).
- tokens: No cost accounting (bounded search).
- subscription_allowance: Shows subscription limit windows (% used) for supported agents.
- provider_reconciliation: No cost accounting (bounded search).
- compute_cost: No cost accounting (bounded search).
- refresh_delay: Configurable check interval.
- alerts: No cost accounting (bounded search).
- export: No cost accounting (bounded search).
- drilldown: No cost accounting (bounded search).

- task_cost — Task cost [unsupported]: No cost accounting (bounded search). Sources: runner:srch-cost.
- session_cost — Session cost [unsupported]: No cost accounting (bounded search). Sources: runner:srch-cost.
- child_cost — Child cost [unsupported]: No cost accounting (bounded search). Sources: runner:srch-cost.
- epic_cost — Epic cost [unsupported]: No cost accounting (bounded search). Sources: runner:srch-cost.
- harness_aggregation — Harness aggregation [unsupported]: No aggregation across harnesses. Sources: runner:srch-cost.
- billed_vs_estimated — Billed vs estimated [unsupported]: No cost accounting (bounded search). Sources: runner:srch-cost.
- tokens — Tokens [unsupported]: No cost accounting (bounded search). Sources: runner:srch-cost.
- subscription_allowance — Subscription allowance [partial]: Shows subscription limit windows (% used) for supported agents. Sources: runner:arch, runner:claude-acc.
- provider_reconciliation — Provider reconciliation [unsupported]: No cost accounting (bounded search). Sources: runner:srch-cost.
- compute_cost — Compute cost [unsupported]: No cost accounting (bounded search). Sources: runner:srch-cost.
- refresh_delay — Refresh delay [partial]: Configurable check interval. Sources: runner:claude-acc.
- alerts — Alerts [unsupported]: No cost accounting (bounded search). Sources: runner:srch-cost.
- export — Export [unsupported]: No cost accounting (bounded search). Sources: runner:srch-cost.
- drilldown — Drilldown [unsupported]: No cost accounting (bounded search). Sources: runner:srch-cost.

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

Sources: runner:arch, runner:srch-cost, runner:claude-acc

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

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

No queues, resource limits or deduplication of checks.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- concurrency: No such feature (bounded search).
- queues: No such feature (bounded search).
- cpu_ram: No such feature (bounded search).
- backpressure: No such feature (bounded search).
- host_awareness: No such feature (bounded search).
- check_reuse: No such feature (bounded search).
- check_deduplication: No such feature (bounded search).
- bounded_tests: No such feature (bounded search).
- cancellation: No such feature (bounded search).
- fairness: No such feature (bounded search).
- recovery: No such feature (bounded search).
- shared_limits: No such feature (bounded search).

- concurrency — Concurrency [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.
- queues — Queues [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.
- cpu_ram — Cpu ram [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.
- backpressure — Backpressure [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.
- host_awareness — Host awareness [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.
- check_reuse — Check reuse [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.
- check_deduplication — Check deduplication [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.
- bounded_tests — Bounded tests [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.
- cancellation — Cancellation [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.
- fairness — Fairness [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.
- recovery — Recovery [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.
- shared_limits — Shared limits [unsupported]: No such feature (bounded search). Sources: runner:srch-limits.

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

Sources: runner:srch-limits

## Human collaboration and control

### TEAM-01: Live human collaboration

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

Single-user local app; remote control by the same account on another computer; no sharing or co-prompting.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- visibility: No multi-user code (bounded search); remote access is account-bound.
- discussion: No multi-user code (bounded search); remote access is account-bound.
- comments: No multi-user code (bounded search); remote access is account-bound.
- presence: No multi-user code (bounded search); remote access is account-bound.
- coprompting: No multi-user code (bounded search); remote access is account-bound.
- ordering: No multi-user code (bounded search); remote access is account-bound.
- conflicts: No multi-user code (bounded search); remote access is account-bound.
- attribution: No multi-user code (bounded search); remote access is account-bound.
- permissions: No multi-user code (bounded search); remote access is account-bound.
- plan_restrictions: No multi-user code (bounded search); remote access is account-bound.
- owner_online: No multi-user code (bounded search); remote access is account-bound.

- visibility — Visibility [unsupported]: No multi-user code (bounded search); remote access is account-bound. Sources: runner:srch-team, runner:remote.
- discussion — Discussion [unsupported]: No multi-user code (bounded search); remote access is account-bound. Sources: runner:srch-team, runner:remote.
- comments — Comments [unsupported]: No multi-user code (bounded search); remote access is account-bound. Sources: runner:srch-team, runner:remote.
- presence — Presence [unsupported]: No multi-user code (bounded search); remote access is account-bound. Sources: runner:srch-team, runner:remote.
- coprompting — Coprompting [unsupported]: No multi-user code (bounded search); remote access is account-bound. Sources: runner:srch-team, runner:remote.
- ordering — Ordering [unsupported]: No multi-user code (bounded search); remote access is account-bound. Sources: runner:srch-team, runner:remote.
- conflicts — Conflicts [unsupported]: No multi-user code (bounded search); remote access is account-bound. Sources: runner:srch-team, runner:remote.
- attribution — Attribution [unsupported]: No multi-user code (bounded search); remote access is account-bound. Sources: runner:srch-team, runner:remote.
- permissions — Permissions [unsupported]: No multi-user code (bounded search); remote access is account-bound. Sources: runner:srch-team, runner:remote.
- plan_restrictions — Plan restrictions [unsupported]: No multi-user code (bounded search); remote access is account-bound. Sources: runner:srch-team, runner:remote.
- owner_online — Owner online [unsupported]: No multi-user code (bounded search); remote access is account-bound. Sources: runner:srch-team, runner:remote.

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

Sources: runner:remote, runner:srch-team

### TEAM-02: Roles and access boundaries

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

No roles, organizations or SSO.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- organization_roles: No roles, membership or SSO (bounded search).
- project_roles: No roles, membership or SSO (bounded search).
- task_roles: No roles, membership or SSO (bounded search).
- membership: No roles, membership or SSO (bounded search).
- sso: No roles, membership or SSO (bounded search).
- provisioning: No roles, membership or SSO (bounded search).
- unauthorized_access: No roles, membership or SSO (bounded search).
- revocation: No roles, membership or SSO (bounded search).
- plan_scope: No roles, membership or SSO (bounded search).

- organization_roles — Organization roles [unsupported]: No roles, membership or SSO (bounded search). Sources: runner:srch-team.
- project_roles — Project roles [unsupported]: No roles, membership or SSO (bounded search). Sources: runner:srch-team.
- task_roles — Task roles [unsupported]: No roles, membership or SSO (bounded search). Sources: runner:srch-team.
- membership — Membership [unsupported]: No roles, membership or SSO (bounded search). Sources: runner:srch-team.
- sso — Sso [unsupported]: No roles, membership or SSO (bounded search). Sources: runner:srch-team.
- provisioning — Provisioning [unsupported]: No roles, membership or SSO (bounded search). Sources: runner:srch-team.
- unauthorized_access — Unauthorized access [unsupported]: No roles, membership or SSO (bounded search). Sources: runner:srch-team.
- revocation — Revocation [unsupported]: No roles, membership or SSO (bounded search). Sources: runner:srch-team.
- plan_scope — Plan scope [unsupported]: No roles, membership or SSO (bounded search). Sources: runner:srch-team.

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

Sources: runner:srch-team

### TEAM-03: Approvals and temporary access

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

Agent permission behavior is the agent own: chats default to the agent configuration, Bypass toggles are opt-in, and missions always use broad access.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- command: Chats follow each agent approval setting unless Bypass is on; Needs you reports waits.
- tool: Same.
- network: None.
- secret: None.
- delivery: None.
- approver_identity: Single user.
- lifetime: None.
- revoke: Pairing can be revoked for remote devices.
- tunnels: No tunnels besides the relay.
- safer_modes: Leave Bypass off for chats; pi uses trusted workspace.
- enforcement: Not product-enforced; goal text sets limits.

- command — Command [partial]: Chats follow each agent approval setting unless Bypass is on; Needs you reports waits. Sources: runner:agents-doc.
- tool — Tool [partial]: Same. Sources: runner:agents-doc.
- network — Network [unsupported]: None. Sources: runner:missions.
- secret — Secret [unsupported]: None. Sources: runner:missions.
- delivery — Delivery [unsupported]: None. Sources: runner:srch-pr.
- approver_identity — Approver identity [unsupported]: Single user. Sources: runner:srch-team.
- lifetime — Lifetime [unsupported]: None. Sources: runner:missions.
- allow — Allow [supported]: Answer approvals in the agent terminal. Sources: runner:agents-doc.
- deny — Deny [supported]: Same. Sources: runner:agents-doc.
- revoke — Revoke [partial]: Pairing can be revoked for remote devices. Sources: runner:remote.
- tunnels — Tunnels [unknown]: No tunnels besides the relay.
- defaults — Defaults [supported]: Chat Bypass off by default; missions broad access by default. Sources: runner:agents-doc, runner:missions.
- safer_modes — Safer modes [partial]: Leave Bypass off for chats; pi uses trusted workspace. Sources: runner:agents-doc.
- enforcement — Enforcement [unsupported]: Not product-enforced; goal text sets limits. Sources: runner:missions.

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

Sources: runner:agents-doc, runner:missions, runner:srch-pr, runner:srch-team, runner:remote

### TEAM-04: Decision and activity history

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

Persistent mission feed and session history locally; no attribution of humans, audit or export.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- actions: Feed records messages, questions and lifecycle events.
- approvals: Approvals not recorded by Runner.
- edits: None.
- decisions: Answers on feed cards.
- cross_user_persistence: Single user.
- export: No export.
- mutability: Not stated.
- retention: Not stated.
- integrity: No integrity guarantee; no fsync by design.

- actions — Actions [partial]: Feed records messages, questions and lifecycle events. Sources: runner:missions.
- approvals — Approvals [unsupported]: Approvals not recorded by Runner. Sources: runner:agents-doc.
- edits — Edits [unsupported]: None. Sources: runner:chats.
- discussion — Discussion [supported]: Feed. Sources: runner:missions.
- decisions — Decisions [partial]: Answers on feed cards. Sources: runner:missions.
- cross_user_persistence — Cross user persistence [unsupported]: Single user. Sources: runner:srch-team.
- cross_session_persistence — Cross session persistence [supported]: SQLite and event log. Sources: runner:arch.
- export — Export [unsupported]: No export. Sources: runner:srch-issue.
- mutability — Mutability [unknown]: Not stated.
- retention — Retention [unknown]: Not stated.
- integrity — Integrity [unsupported]: No integrity guarantee; no fsync by design. Sources: runner:arch.

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

Sources: runner:missions, runner:arch, runner:agents-doc, runner:chats, runner:srch-team, runner:srch-issue

### TEAM-05: Review experience and guidance

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

Files view with git status and a read-only Changes view with per-file diffs and mark-viewed beside agents; no comments, request-changes or review queue.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- pending_reviews: Changes lists files with uncommitted changes and commits ahead.
- evidence_navigation: Open files, terminal links ⌘-click.
- comments: No comments.
- request_changes: Message the reviewer/coder in the feed.
- shipping_guidance: None.
- effort: Not published.
- missed_evidence: Mark viewed dims files.
- narrow_screen: Desktop only.
- roles: Reviewer role in the default crew.

- pending_reviews — Pending reviews [partial]: Changes lists files with uncommitted changes and commits ahead. Sources: runner:chats.
- change_understanding — Change understanding [supported]: Per-file diff, line counts and rename info. Sources: runner:chats.
- evidence_navigation — Evidence navigation [partial]: Open files, terminal links ⌘-click. Sources: runner:chats, runner:sessions.
- comments — Comments [unsupported]: No comments. Sources: runner:srch-pr.
- request_changes — Request changes [partial]: Message the reviewer/coder in the feed. Sources: runner:missions.
- shipping_guidance — Shipping guidance [unsupported]: None. Sources: runner:srch-pr.
- effort — Effort [unknown]: Not published.
- missed_evidence — Missed evidence [partial]: Mark viewed dims files. Sources: runner:chats.
- keyboard — Keyboard [supported]: Shortcut-driven (Space, C, arrows) and a keyboard shortcuts reference. Sources: runner:chats.
- narrow_screen — Narrow screen [unknown]: Desktop only.
- context_switching — Context switching [supported]: Split tabs and side panel. Sources: runner:readme, runner:chats.
- roles — Roles [partial]: Reviewer role in the default crew. Sources: runner:crews.
- retained_context — Retained context [supported]: Panel state persisted per mission. Sources: runner:missions.

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

Sources: runner:chats, runner:sessions, runner:srch-pr, runner:missions, runner:readme, runner:crews

### TEAM-06: Colleague takeover and continuity

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

No colleague takeover; the same account can take a session over from another of its computers in the private beta.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- ongoing_takeover: Another computer on the same account can take terminal control (private beta).
- same_task: Same missions and chats of the host.
- decisions: Feed answers.
- artifacts: None.
- permissions: PIN pairing per device; revoke devices.
- owner_disconnect: Host must be awake and signed in.
- ownership: No transfer.
- attribution: No attribution.
- context_loss: Not stated.
- harness_transfer: No cross-harness transfer.

- ongoing_takeover — Ongoing takeover [partial]: Another computer on the same account can take terminal control (private beta). Sources: runner:remote.
- same_task — Same task [partial]: Same missions and chats of the host. Sources: runner:remote.
- session_history — Session history [supported]: Remote opens live terminals and feed. Sources: runner:remote.
- decisions — Decisions [partial]: Feed answers. Sources: runner:remote.
- artifacts — Artifacts [unsupported]: None. Sources: runner:srch-issue.
- permissions — Permissions [partial]: PIN pairing per device; revoke devices. Sources: runner:remote.
- runtime_context — Runtime context [supported]: Execution stays on the host. Sources: runner:remote.
- owner_disconnect — Owner disconnect [unsupported]: Host must be awake and signed in. Sources: runner:remote.
- ownership — Ownership [unsupported]: No transfer. Sources: runner:srch-team.
- attribution — Attribution [unsupported]: No attribution. Sources: runner:srch-team.
- context_loss — Context loss [unknown]: Not stated.
- harness_transfer — Harness transfer [unsupported]: No cross-harness transfer. Sources: runner:agents-doc.

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

Sources: runner:remote, runner:srch-issue, runner:srch-team, runner:agents-doc

## Verification and delivery

### SHIP-01: Retained artifacts and outputs

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

Terminal output, mission feed and read-only file and diff views; no artifact gallery.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- documents: Markdown rendered in Files.
- screenshots: None.
- recordings: None.
- previews: No preview server integration.
- test_outputs: In terminals only.
- reviewer_outputs: Reviewer member messages in the feed.
- gallery: None.
- task_links: None.
- revision_links: None.
- prompt_leakage: Not assessed.

- diffs — Diffs [supported]: Changes view diffs. Sources: runner:chats.
- documents — Documents [partial]: Markdown rendered in Files. Sources: runner:chats.
- screenshots — Screenshots [unsupported]: None. Sources: runner:srch-issue.
- recordings — Recordings [unsupported]: None. Sources: runner:srch-issue.
- previews — Previews [unsupported]: No preview server integration. Sources: runner:chats.
- test_outputs — Test outputs [partial]: In terminals only. Sources: runner:sessions.
- reviewer_outputs — Reviewer outputs [partial]: Reviewer member messages in the feed. Sources: runner:missions.
- gallery — Gallery [unsupported]: None. Sources: runner:srch-issue.
- task_links — Task links [unsupported]: None. Sources: runner:srch-issue.
- revision_links — Revision links [unsupported]: None. Sources: runner:srch-issue.
- persistence — Persistence [supported]: Feed persists. Sources: runner:missions.
- child_findings — Child findings [supported]: Member messages retained. Sources: runner:missions.
- prompt_leakage — Prompt leakage [unknown]: Not assessed.

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

Sources: runner:chats, runner:missions, runner:srch-issue, runner:sessions

### SHIP-02: Verification and spec gates

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

No gates; conventions can require checks but are instructions to the agents.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- tests: No gate in the product (bounded search).
- lint: No gate in the product (bounded search).
- types: No gate in the product (bounded search).
- ci: No gate in the product (bounded search).
- independent_review: Default crew has a reviewer agent role, as an instruction.
- spec_checks: No gate in the product (bounded search).
- required_checks: No gate in the product (bounded search).
- failure_blocking: No gate in the product (bounded search).
- requirement_conflicts: No gate in the product (bounded search).
- configured_policy: Team conventions text.
- enforced_policy: No gate in the product (bounded search).

- tests — Tests [unsupported]: No gate in the product (bounded search). Sources: runner:srch-pr.
- lint — Lint [unsupported]: No gate in the product (bounded search). Sources: runner:srch-pr.
- types — Types [unsupported]: No gate in the product (bounded search). Sources: runner:srch-pr.
- ci — Ci [unsupported]: No gate in the product (bounded search). Sources: runner:srch-pr.
- independent_review — Independent review [partial]: Default crew has a reviewer agent role, as an instruction. Sources: runner:crews.
- spec_checks — Spec checks [unsupported]: No gate in the product (bounded search). Sources: runner:srch-pr.
- required_checks — Required checks [unsupported]: No gate in the product (bounded search). Sources: runner:srch-pr.
- failure_blocking — Failure blocking [unsupported]: No gate in the product (bounded search). Sources: runner:srch-pr.
- requirement_conflicts — Requirement conflicts [unsupported]: No gate in the product (bounded search). Sources: runner:srch-pr.
- configured_policy — Configured policy [partial]: Team conventions text. Sources: runner:crews.
- enforced_policy — Enforced policy [unsupported]: No gate in the product (bounded search). Sources: runner:srch-pr.

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

Sources: runner:crews, runner:srch-pr

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

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

No Git operations of its own; shows worktrees, status and diffs and lets agents run Git per the goal.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- branches: Shows branch and commits ahead.
- worktrees: Picker lists existing worktrees; none created.
- commits: Agents commit if authorized by goal.
- pull_requests: None.
- comments: None.
- ci_response: None.
- rebase: None.
- conflicts: Conflict badges in Changes.
- product_state: Git state read on demand.

- branches — Branches [partial]: Shows branch and commits ahead. Sources: runner:chats.
- worktrees — Worktrees [partial]: Picker lists existing worktrees; none created. Sources: runner:chats, runner:build-crew.
- commits — Commits [unsupported]: Agents commit if authorized by goal. Sources: runner:missions.
- pull_requests — Pull requests [unsupported]: None. Sources: runner:srch-pr.
- comments — Comments [unsupported]: None. Sources: runner:srch-pr.
- ci_response — Ci response [unsupported]: None. Sources: runner:srch-pr.
- rebase — Rebase [unsupported]: None. Sources: runner:srch-pr.
- conflicts — Conflicts [partial]: Conflict badges in Changes. Sources: runner:chats.
- product_state — Product state [unsupported]: Git state read on demand. Sources: runner:chats.

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

Sources: runner:chats, runner:missions, runner:build-crew, runner:srch-pr

### SHIP-04: Merge and deployment authority

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

No approve, merge, release or deploy authority.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- approve: None (bounded search).
- merge: None (bounded search).
- release: None (bounded search).
- deploy: None (bounded search).
- exact_revision: None (bounded search).
- authority_enforcement: None (bounded search).

- approve — Approve [unsupported]: None (bounded search). Sources: runner:srch-pr.
- merge — Merge [unsupported]: None (bounded search). Sources: runner:srch-pr.
- release — Release [unsupported]: None (bounded search). Sources: runner:srch-pr.
- deploy — Deploy [unsupported]: None (bounded search). Sources: runner:srch-pr.
- exact_revision — Exact revision [unsupported]: None (bounded search). Sources: runner:srch-pr.
- authority_enforcement — Authority enforcement [unsupported]: None (bounded search). Sources: runner:srch-pr.

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

Sources: runner:srch-pr

### SHIP-05: Completion evidence and rollback

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

No delivery evidence or rollback.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- commit_links: None (bounded search).
- pr_links: None (bounded search).
- build_links: None (bounded search).
- deployment_links: None (bounded search).
- delivery_status: None (bounded search).
- retained_evidence: None (bounded search).
- rollback: None (bounded search).
- revert: None (bounded search).
- stale_approval_invalidation: None (bounded search).

- commit_links — Commit links [unsupported]: None (bounded search). Sources: runner:srch-pr.
- pr_links — Pr links [unsupported]: None (bounded search). Sources: runner:srch-pr.
- build_links — Build links [unsupported]: None (bounded search). Sources: runner:srch-pr.
- deployment_links — Deployment links [unsupported]: None (bounded search). Sources: runner:srch-pr.
- delivery_status — Delivery status [unsupported]: None (bounded search). Sources: runner:srch-pr.
- retained_evidence — Retained evidence [unsupported]: None (bounded search). Sources: runner:srch-pr.
- rollback — Rollback [unsupported]: None (bounded search). Sources: runner:srch-pr.
- revert — Revert [unsupported]: None (bounded search). Sources: runner:srch-pr.
- stale_approval_invalidation — Stale approval invalidation [unsupported]: None (bounded search). Sources: runner:srch-pr.

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

Sources: runner:srch-pr

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

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

No batch review; per-file mark-viewed and a read-only diff.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- review_queue: None (bounded search).
- summaries: None (bounded search).
- grouping: None (bounded search).
- risk_size_filters: None (bounded search).
- findings: None (bounded search).
- artifacts: None (bounded search).
- request_changes: None (bounded search).
- exact_revision_approval: None (bounded search).
- dependency_queues: None (bounded search).
- next_actions: Mark viewed advances to the next file.
- stale_approval_invalidation: None (bounded search).
- check_deduplication: None (bounded search).

- review_queue — Review queue [unsupported]: None (bounded search). Sources: runner:srch-pr.
- summaries — Summaries [unsupported]: None (bounded search). Sources: runner:srch-pr.
- grouping — Grouping [unsupported]: None (bounded search). Sources: runner:srch-pr.
- risk_size_filters — Risk size filters [unsupported]: None (bounded search). Sources: runner:srch-pr.
- findings — Findings [unsupported]: None (bounded search). Sources: runner:srch-pr.
- artifacts — Artifacts [unsupported]: None (bounded search). Sources: runner:srch-pr.
- request_changes — Request changes [unsupported]: None (bounded search). Sources: runner:srch-pr.
- exact_revision_approval — Exact revision approval [unsupported]: None (bounded search). Sources: runner:srch-pr.
- dependency_queues — Dependency queues [unsupported]: None (bounded search). Sources: runner:srch-pr.
- next_actions — Next actions [partial]: Mark viewed advances to the next file. Sources: runner:chats.
- stale_approval_invalidation — Stale approval invalidation [unsupported]: None (bounded search). Sources: runner:srch-pr.
- check_deduplication — Check deduplication [unsupported]: None (bounded search). Sources: runner:srch-pr.

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

Sources: runner:chats, runner:srch-pr

## Ownership, privacy and economics

### OWN-01: Source and license

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

MIT for the whole repository (desktop app, daemon, CLI); the relay service is closed and hosted; versions from 2026-08-22 to 2026-09-22 were GPL-3.0-only.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- server_license: Daemon and CLI are MIT; relay server is not in the public repository.
- hosted_extensions: Hosted relay and account service closed.
- hosted_parity: Hosted relay not inspectable.

- client_license — Client license [supported]: MIT. Sources: runner:license.
- server_license — Server license [partial]: Daemon and CLI are MIT; relay server is not in the public repository. Sources: runner:license, runner:remote.
- hosted_extensions — Hosted extensions [partial]: Hosted relay and account service closed. Sources: runner:remote.
- source_visibility — Source visibility [supported]: Public repository. Sources: runner:repoapi.
- source_revision — Source revision [supported]: v0.20.0 commit c6ce633. Sources: runner:release.
- hosted_parity — Hosted parity [unknown]: Hosted relay not inspectable. Sources: runner:remote.

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

Sources: runner:license, runner:repoapi, runner:remote, runner:release

### OWN-02: Hosting and exit

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

Fully local data (SQLite and event logs); works without any account; relay optional; no export feature documented.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- vendor_dependencies: Optional relay/account; Sparkle/appcast updates from releases.
- export: None.
- import: None.
- formats: SQLite and event-log files; agent conversations in agent stores.
- cancellation: Relay account terms not published.
- history_portability: Agent histories live in agent folders.

- self_hosting — Self hosting [supported]: Runs locally with no vendor service. Sources: runner:arch, runner:remote.
- vendor_dependencies — Vendor dependencies [partial]: Optional relay/account; Sparkle/appcast updates from releases. Sources: runner:remote, runner:install.
- export — Export [unsupported]: None. Sources: runner:srch-issue.
- import — Import [unsupported]: None. Sources: runner:srch-issue.
- formats — Formats [partial]: SQLite and event-log files; agent conversations in agent stores. Sources: runner:arch.
- cancellation — Cancellation [unknown]: Relay account terms not published.
- account_independence — Account independence [supported]: Everything but remote access works signed out. Sources: runner:remote.
- history_portability — History portability [partial]: Agent histories live in agent folders. Sources: runner:arch.

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

Sources: runner:arch, runner:remote, runner:install, runner:srch-issue

### OWN-03: Data handling and telemetry

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

Sessions and history stay on the machine; remote relay carries end-to-end encrypted traffic; no telemetry code found; no privacy policy page.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- credentials: Agent logins stay in agent configs; relay keys stored in OS keystore on release builds; PIN not sent to the service.
- retention: No retention terms for relay metadata.
- deletion: Delete missions; Reset remote access clears identity.
- training: Provider policies third-party.
- residency: Relay region not stated beyond mainland China.
- subprocessors: No list.
- telemetry_disclosure: No privacy page (404); docs silent.
- telemetry_controls: None because no telemetry exists.
- consent_prompt: No first-run consent dialog found.

- code_data — Code data [supported]: Local; goes only to the agents providers. Sources: runner:readme.
- prompts — Prompts [supported]: Local. Sources: runner:readme.
- credentials — Credentials [partial]: Agent logins stay in agent configs; relay keys stored in OS keystore on release builds; PIN not sent to the service. Sources: runner:remote.
- logs — Logs [supported]: Local log folder. Sources: runner:arch.
- artifacts — Artifacts [supported]: Local. Sources: runner:readme.
- retention — Retention [unknown]: No retention terms for relay metadata.
- deletion — Deletion [partial]: Delete missions; Reset remote access clears identity. Sources: runner:remote.
- training — Training [unknown]: Provider policies third-party.
- residency — Residency [unknown]: Relay region not stated beyond mainland China. Sources: runner:remote.
- subprocessors — Subprocessors [unknown]: No list.
- telemetry_disclosure — Telemetry disclosure [unknown]: No privacy page (404); docs silent. Sources: runner:site.
- telemetry_defaults — Telemetry defaults [supported]: No telemetry code in the pinned release. Sources: runner:srch-tele.
- telemetry_controls — Telemetry controls [unsupported]: None because no telemetry exists. Sources: runner:srch-tele.
- consent_prompt — Consent prompt [unsupported]: No first-run consent dialog found. Sources: runner:srch-tele.
- provider_separation — Provider separation [supported]: Agent providers handled by agent CLIs. Sources: runner:install.

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

Sources: runner:readme, runner:remote, runner:srch-tele, runner:arch, runner:site, runner:install

### OWN-04: Price and included usage

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

Free MIT software; donations via Ko-fi and Afdian; no paid plan found; remote access service pricing unpublished.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- currency: No price.
- interval: No subscription.
- seats: No seats.
- seat_minimum: None.
- credits: None.
- trial: None; free.
- overages: None.
- taxes: Not applicable.

- currency — Currency [unsupported]: No price. Sources: runner:readme.
- interval — Interval [unsupported]: No subscription. Sources: runner:readme.
- seats — Seats [unsupported]: No seats. Sources: runner:readme.
- seat_minimum — Seat minimum [unsupported]: None. Sources: runner:readme.
- workspace_fees — Workspace fees [supported]: None. Sources: runner:readme.
- included_usage — Included usage [supported]: No usage metering. Sources: runner:readme.
- credits — Credits [unsupported]: None. Sources: runner:readme.
- trial — Trial [unsupported]: None; free. Sources: runner:readme.
- overages — Overages [unsupported]: None. Sources: runner:readme.
- taxes — Taxes [unknown]: Not applicable.
- model_cost — Model cost [supported]: Agent subscriptions or APIs billed by providers. Sources: runner:install.
- compute_cost — Compute cost [supported]: Own machine. Sources: runner:install.

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

Sources: runner:readme, runner:license, runner:site, runner:install

### OWN-05: Scenario cost and controls

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

The app costs nothing; scenario costs are the agent subscriptions or API usage of each developer.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- one_person: App cost zero; agent costs separate.
- two_people: Two independent installs; no collaboration features.
- five_people: Five independent installs.
- task_assumptions: No scenario assumptions.
- concurrency: None.
- tokens: None.
- compute_hours: User machines.
- variable_cost: Agent costs.
- included_cost: None.
- unknown_cost: Relay service pricing unknown.

- one_person — One person [partial]: App cost zero; agent costs separate. Sources: runner:readme, runner:install.
- two_people — Two people [partial]: Two independent installs; no collaboration features. Sources: runner:readme, runner:srch-team.
- five_people — Five people [partial]: Five independent installs. Sources: runner:readme.
- task_assumptions — Task assumptions [unknown]: No scenario assumptions.
- concurrency — Concurrency [unknown]: None.
- tokens — Tokens [unknown]: None.
- compute_hours — Compute hours [unknown]: User machines.
- fixed_cost — Fixed cost [supported]: Zero for the app. Sources: runner:readme.
- variable_cost — Variable cost [partial]: Agent costs. Sources: runner:install.
- included_cost — Included cost [unsupported]: None. Sources: runner:readme.
- unknown_cost — Unknown cost [partial]: Relay service pricing unknown. Sources: runner:remote.

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

Sources: runner:readme, runner:install, runner:srch-team, runner:remote

### OWN-06: Availability and support

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

Alpha with releases every few days, public issues and Discord; no SLA or status page.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- response_commitments: None stated.
- status_history: No status page.
- deprecation: License changed twice (GPL window 2026-08-22 to 2026-09-22).
- export_options: None.

- release_stage — Release stage [supported]: README labels the product Alpha; Linux beta; remote access and iPhone private beta. Sources: runner:readme, runner:site.
- access_restrictions — Access restrictions [supported]: Remote access invite-only, mainland China. Sources: runner:remote.
- support — Support [supported]: Discord, GitHub issues, WeChat group. Sources: runner:readme.
- response_commitments — Response commitments [unsupported]: None stated. Sources: runner:readme.
- release_activity — Release activity [supported]: v0.19.8 2026-11-12, v0.19.9 2026-11-14, v0.20.0 2026-11-16 plus nightlies. Sources: runner:release.
- status_history — Status history [unknown]: No status page.
- deprecation — Deprecation [partial]: License changed twice (GPL window 2026-08-22 to 2026-09-22). Sources: runner:license.
- export_options — Export options [unsupported]: None. Sources: runner:srch-issue.

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

Sources: runner:release, runner:repoapi, runner:readme, runner:site, runner:remote, runner:license, runner:srch-issue

### OWN-07: Enterprise assurance

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

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

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

Free open-source download without caps; remote access is invite-only beta.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- trial: No trial; free.
- credits_trial: None.
- paid_only: Nothing paid-only found.
- free_scenarios: Local parallel agents and review free; no collaboration, issue management or remote compute.
- card_required: None.
- usage_caps: None.
- paid_evaluation: None.

- ongoing_free — Ongoing free [supported]: Free app. Sources: runner:readme.
- trial — Trial [unsupported]: No trial; free. Sources: runner:readme.
- credits_trial — Credits trial [unsupported]: None. Sources: runner:readme.
- self_host_cost — Self host cost [supported]: Own machines and agent costs. Sources: runner:install.
- paid_only — Paid only [unsupported]: Nothing paid-only found. Sources: runner:readme.
- early_access — Early access [supported]: Remote access and iPhone are gated beta. Sources: runner:remote, runner:site.
- free_scenarios — Free scenarios [partial]: Local parallel agents and review free; no collaboration, issue management or remote compute. Sources: runner:readme, runner:srch-team.
- card_required — Card required [unsupported]: None. Sources: runner:readme.
- usage_caps — Usage caps [unsupported]: None. Sources: runner:readme.
- paid_evaluation — Paid evaluation [unsupported]: None. Sources: runner:readme.

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

Sources: runner:readme, runner:remote, runner:install, runner:site, runner:srch-team

### OWN-09: Pricing transparency

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

No ADE price exists; remote access pricing unpublished.

Availability: generally-available
Delivery: native
Scope: surfaces=Runner desktop app (Rust/GPUI) for macOS, Windows and Linux beta, runner CLI over the runnerd background service; version=v0.20.0 (commit c6ce633, released 2026-11-16; alpha); plan=Open source (MIT); free; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- units: None.
- included_limits: None.
- overages: None.
- compute_markup: None.
- model_markup: None.
- minimum_commitment: None.
- cancellation: No subscription.
- sales_only_unknowns: Relay service terms unpublished.
- transparency_classification: Free application; relay terms not public.

- units — Units [unsupported]: None. Sources: runner:readme.
- included_limits — Included limits [unsupported]: None. Sources: runner:readme.
- overages — Overages [unsupported]: None. Sources: runner:readme.
- compute_markup — Compute markup [unsupported]: None. Sources: runner:readme.
- model_markup — Model markup [unsupported]: None. Sources: runner:readme.
- minimum_commitment — Minimum commitment [unsupported]: None. Sources: runner:readme.
- cancellation — Cancellation [unsupported]: No subscription. Sources: runner:readme.
- sales_only_unknowns — Sales only unknowns [partial]: Relay service terms unpublished. Sources: runner:remote.
- transparency_classification — Transparency classification [partial]: Free application; relay terms not public. Sources: runner:readme, runner:remote.

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

Sources: runner:readme, runner:remote

## Sources

### runner:readme

Runner README. Native macOS/Windows (Linux beta) app where Claude Code, Codex, Antigravity, Copilot CLI, pi and others run in real terminals; reusable crews and missions with a shared feed; runner CLI; remote control private beta; MIT.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/README.md
- Locator: Features; Also included; Supported agents; License
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:install

Install Runner. macOS 12+, Windows 10 1809+ x64, Linux beta (glibc 2.35+, ARM64 and x86_64); agent CLIs provide their own model connection and accounts; first-run Setup detects agents.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/getting-started/install.md
- Locator: Download the app table; Set up an agent
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:cli-doc

CLI reference. runner commands: remote, daemon, status, project, role, crew, mission (start, stop, resume, feed, answer, link), chat start, session (list, stop, resume, restart), msg; --json output; works with app closed.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/reference/cli.md
- Locator: Command overview
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:drive

Drive Runner from agents. Installs a Runner skill for detected agents so an agent can start missions, follow the feed and message members; missions started from a chat link back and report.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/guides/drive-runner-from-agents.md
- Locator: Discover the installed version; Start and follow a crew
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:missions

Missions. Mission = goal, per-member terminals, persistent feed; states Needs you/Failed/Interrupted/Working/Settled/Ended; shared directory, no branches or worktrees; mission launches use broad-access permissions; stop, resume, restart slot, archive.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/concepts/missions.md
- Locator: Goal and membership; Feed; Linked chat and reports; Permissions; Stop, resume and archive
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:chats

Chats and windows. Side panel Files with git status and worktree picker, read-only Changes view with per-file diffs and mark-viewed, desktop notifications, split tabs and windows.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/guides/chats-and-windows.md
- Locator: Files view; Changes; Notifications
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:remote

Remote access. Private beta, invite-only, mainland China; hosted relay with end-to-end encrypted sessions and PIN pairing; signed-out Runner works locally only; remote access never stops sessions.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/guides/remote-access.md
- Locator: Sign in; Through Runner relay; PIN pairing
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:site

runnersh.dev home page. Site banner: Runner for iPhone and remote access are in private beta with an iPhone waitlist; links to Docs and Release notes; no pricing page (404).

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/README.md
- Locator: banner
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:release

Runner v0.20.0 release. Stable release 2026-11-16 with signed macOS arm64/x64 DMGs, Windows x64 setup exe, Linux arm64/x64 deb and tarballs, appcast feeds; v0.19.9 on 2026-11-14, v0.19.8 on 2026-11-12; a rolling nightly prerelease.

- URL: https://github.com/yicheng47/runner/releases/tag/v0.20.0
- Locator: release assets
- Evidence kind: documented
- Source date: 2026-11-16
- Retrieved: 2026-11-16

### runner:srch-team

Bounded search: organization|rbac|sso|oidc|saml|invite member|presence|co-edit. No multi-user collaboration, roles or SSO; account sign-in exists only for the relay and pairing is per-account computers.

- URL: https://github.com/yicheng47/runner/tree/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Locator: grep -rniE "organization|rbac|sso|oidc|saml|invite member|presence|co-edit" over crates docs/guide README.md at v0.20.0
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Path: crates

### runner:agents-doc

Supported agents. Codex, Claude Code, Antigravity CLI, pi, Copilot CLI, Cursor, Grok Build, OpenCode v2 and opt-in TRAE; separately installed CLIs keep native TUI; per-agent capability table; Bypass defaults off for chats; missions use broad access.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/reference/supported-agents.md
- Locator: Install and sign in; Capabilities; Launch options
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:crews

Crews. Reusable teams of role slots with unique handles, per-slot agent/model/effort overrides and shared team conventions; starter Pair coding crew.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/concepts/crews.md
- Locator: Slots; Team conventions
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:arch

Architecture. Three-process model: GPUI app, runnerd daemon (SQLite, session manager, event bus) and runner CLI over runnerd.sock; sessions survive app quit; usage module reads Claude Code, Codex and Antigravity limits; Claude/Codex update checks disabled inside sessions.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/arch/arch.md
- Locator: Overview; usage module; agent updates; mission inbox
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Path: docs/arch/arch.md

### runner:claude-acc

Claude Code accounts. Multiple Claude Code sign-ins in separate config folders with a usage popover showing weekly usage.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/guides/claude-accounts.md
- Locator: Add an account; Switch the active account
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:srch-cost

Bounded search: cost|dollar|price per|billing. No per-task or dollar cost accounting; usage shows plan-limit percentages for Claude Code, Codex and Antigravity CLI.

- URL: https://github.com/yicheng47/runner/tree/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Locator: grep -rniE "cost|dollar|price per|billing" over crates docs/guide README.md at v0.20.0
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Path: crates

### runner:first-mission

First mission. Runner starts the crew in the directory given and does not create an isolated copy or Git worktree.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/getting-started/first-mission.md
- Locator: directory note
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:srch-pr

Bounded search: pull request|gh pr|merge request|git push|git commit. No PR, push or commit operations in the product; the mission goal tells agents which Git actions are authorized.

- URL: https://github.com/yicheng47/runner/tree/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Locator: grep -rniE "pull request|gh pr|merge request|git push|git commit" over crates docs/guide README.md at v0.20.0
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Path: crates

### runner:process

Process model. Daemon keeps running without clients; Ask/Keep/Stop on app quit; app crash leaves daemon sessions running; daemon crash closes PTYs on macOS and kills sessions.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/arch/process-model.md
- Locator: runnerd lifecycle
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Path: docs/arch/process-model.md

### runner:srch-sched

Bounded search: cron|schedule|recurring|trigger. No scheduler, cron or event-trigger feature; matches are internal refresh timers (usage polling) and hook triggers.

- URL: https://github.com/yicheng47/runner/tree/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Locator: grep -rniE "cron|schedule|recurring|trigger" over crates docs/guide README.md at v0.20.0
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Path: crates

### runner:mcp-skills

MCP servers and skills. Settings pages list and toggle each agent own MCP servers and skills, editing the native config for new sessions.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/guides/mcp-and-skills.md
- Locator: MCP servers; Skills
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:cargo

Workspace Cargo.toml. Rust workspace version 0.20.0 with crates runner-app, runner-cli, runner-core, runner-daemon, runner-terminal; vendored dependencies under vendor/.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/Cargo.toml
- Locator: workspace package version
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Path: Cargo.toml

### runner:srch-issue

Bounded search: issue tracker|ticket|backlog|kanban|epic|todo list. No issue, ticket or backlog entity; missions are sessions with a goal, not trackable work items.

- URL: https://github.com/yicheng47/runner/tree/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Locator: grep -rniE "issue tracker|ticket|backlog|kanban|epic|todo list" over crates docs/guide README.md at v0.20.0
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Path: crates

### runner:sessions

Sessions. A session is one agent or shell in a real terminal; hooks or terminal activity report state; stop, resume, restart actions.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/concepts/sessions.md
- Locator: Read the state; Choose the right action
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:srch-limits

Bounded search: max_turns|token limit|spend limit|budget|timeout. No turn, token or spend limit enforcement for agents; only operational timeouts for Runner internals (30 s sign-in, 10-minute draft hold).

- URL: https://github.com/yicheng47/runner/tree/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Locator: grep -rniE "max_turns|token limit|spend limit|budget|timeout" over crates docs/guide README.md at v0.20.0
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Path: crates

### runner:build-crew

Build a crew. Runner does not isolate working directories automatically; create a Git worktree before launch if needed.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/guide/guides/build-a-crew.md
- Locator: working directories note
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:linux-service

Runner Linux packages and optional runnerd user service. Linux packages ship runner, runnerd and runner-app plus an optional systemd user service for runnerd; troubleshooting says that if the CLI is used over SSH, start runnerd with systemctl --user first. This documents running the daemon and CLI on a Linux host reached over SSH, but no guide presents remote or server execution as a supported workflow.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/docs/arch/linux.md
- Locator: Optional systemd user service (lines 92-107); docs/guide/guides/troubleshooting.md Linux local builds (line 76); packaging/linux/runnerd.service
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-17
- Commit: c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Path: docs/arch/linux.md

### runner:srch-tele

Bounded search: telemetry|analytics|sentry|posthog|mixpanel|amplitude|plausible. No telemetry or analytics code in the Rust crates or docs; the app makes update, usage, relay and agent-CLI calls only.

- URL: https://github.com/yicheng47/runner/tree/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Locator: grep -rniE "telemetry|analytics|sentry|posthog|mixpanel|amplitude|plausible" over crates docs/guide README.md at v0.20.0
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-16
- Commit: c6ce6337e6c49a67dd4432b414ed739e1ef55ab0
- Path: crates

### runner:license

Runner LICENSE. MIT, copyright 2026 Yicheng Wang; README notes versions released 2026-08-22 to 2026-09-22 were GPL-3.0-only.

- URL: https://github.com/yicheng47/runner/blob/c6ce6337e6c49a67dd4432b414ed739e1ef55ab0/LICENSE
- Locator: MIT License text
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16

### runner:repoapi

GitHub repository API. 521 stars on 2026-11-16; MIT license detected; pushed 2026-11-16; homepage https://runnersh.dev/.

- URL: https://api.github.com/repos/yicheng47/runner
- Locator: stargazers_count, license, pushed_at
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-16
