# ai-devkit

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. The same evidence rules apply to Podium and its competitors, but they do not remove this conflict of interest.

Page: https://adecomparison.com/ade/ai-devkit/
Website: https://github.com/codeaholicguy/ai-devkit
Research: covered

Method: https://adecomparison.com/method/

Rank by must-haves met, then preferences, then name. Read each finding's checked date. Findings stay published after their scheduled recheck. Checks over six months old may be outdated.

## ai-devkit:ACC-01

Finding: AI DevKit has native macOS/Linux CLI/TUI operation; the managed console is unsupported on Windows. The scoped clients are terminal interfaces, with separate Telegram/Slack bridges rather than product web or phone apps.

Verification: sourced
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/13-agent-console.md
Locator: Prerequisites; Start a Managed Agent; Hotkeys; Send a Message
Finding: Interactive TTY console lists agents, previews transcripts, starts/renames/kills agents and connects channels. Named managed start types include Claude, Codex, Gemini CLI, Grok CLI, OpenCode and Pi. Durable mode limited to Claude/Codex/Pi; managed runtime tmux or configured Herdr.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/17-multi-agent-orchestration.md
Locator: Lead vs console; Layout; Skills; Start-then-assign; Known limitations
Finding: Product orchestration skill guides a lead using agent start/send/list to supervise named workers and cross-harness review. Users manually supply separate worktree directories; same-folder session matching may collide. Console experimental on macOS/Linux and unsupported Windows.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/17-multi-agent-orchestration.md
Locator: Prerequisites; packages/cli client tree; web documentation routes; release/package targets
Finding: Managed agent start and experimental terminal console support macOS/Linux and explicitly do not support Windows. The scoped product client tree contains CLI/TUI, without browser, native iOS/Android or phone-browser control clients; its web directory is a documentation site and chat-service bridges are separate.
Retrieved: 2026-11-13

## ai-devkit:ACC-02

Finding: Managed start supports named coding harnesses and supervision across providers; configuration integration alone is not proof that every editor is launchable. AI DevKit cli@0.73.1 registers AntigravityCliAdapter and a startable antigravity_cli runtime whose command is agy. The complete startable runtime registry omits Cursor and Aider.

Verification: sourced
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9 Antigravity source pass: cli@0.73.1 (4a8e19d00ff770ac821f5635144e7d3a12ebcebe).

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.
Antigravity CLI must be installed and authenticated; editor configuration support alone does not establish a startable agent.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/13-agent-console.md
Locator: Prerequisites; Start a Managed Agent; Hotkeys; Send a Message
Finding: Interactive TTY console lists agents, previews transcripts, starts/renames/kills agents and connects channels. Named managed start types include Claude, Codex, Gemini CLI, Grok CLI, OpenCode and Pi. Durable mode limited to Claude/Codex/Pi; managed runtime tmux or configured Herdr.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/4a8e19d00ff770ac821f5635144e7d3a12ebcebe/packages/agent-manager/src/harnesses/runtimeProfiles.ts#L14-L25
Locator: packages/agent-manager/src/harnesses/runtimeProfiles.ts lines 14-25, cli@0.73.1, commit 4a8e19d00ff770ac821f5635144e7d3a12ebcebe
Finding: AI DevKit cli@0.73.1 registers AntigravityCliAdapter and a startable antigravity_cli runtime whose command is agy.
Retrieved: 2026-11-10

Source: https://github.com/codeaholicguy/ai-devkit/blob/4a8e19d00ff770ac821f5635144e7d3a12ebcebe/packages/agent-manager/src/harnesses/index.ts#L1-L32
Locator: packages/agent-manager/src/harnesses/index.ts lines 1-32, cli@0.73.1, commit 4a8e19d00ff770ac821f5635144e7d3a12ebcebe
Finding: AI DevKit cli@0.73.1 registers AntigravityCliAdapter and a startable antigravity_cli runtime whose command is agy.
Retrieved: 2026-11-10

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/packages/agent-manager/src/harnesses/runtimeProfiles.ts
Locator: HARNESS_RUNTIME_PROFILES; adapters/AgentAdapter.ts AGENT_TYPES; managed agent start validation
Finding: The complete startable runtime registry includes Claude, Codex, Copilot, Gemini CLI, Grok CLI, Antigravity CLI, OpenCode, Pi, Kiro, Devin and Muse. Cursor and Aider have no startable runtime profile or coding-harness adapter; configuring editor files is separate.
Retrieved: 2026-11-13

## ai-devkit:ACC-03

Finding: Underlying agent logins/provider credentials supply access. Capacity reads credentials already stored by provider tools.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/15-capacity.md
Locator: Status; Capacity
Finding: Readiness checks are hints, not successful login probes. Capacity reads stored provider credentials and reports quota windows, availability and reset times; it does not establish task billing.
Retrieved: 2026-11-08

## ai-devkit:ACC-04

Finding: Machine setup installs skills/hooks/memory wiring; init writes project config. Console needs interactive TTY and installed agent runtimes.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/13-agent-console.md
Locator: Prerequisites; Start a Managed Agent; Hotkeys; Send a Message
Finding: Interactive TTY console lists agents, previews transcripts, starts/renames/kills agents and connects channels. Named managed start types include Claude, Codex, Gemini CLI, Grok CLI, OpenCode and Pi. Durable mode limited to Claude/Codex/Pi; managed runtime tmux or configured Herdr.
Retrieved: 2026-11-08

## ai-devkit:ACC-05

Finding: CLI exposes managed agent control, memory and daemon operations; memory MCP server provides tool access.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/6-memory.md
Locator: How it works; MCP; CLI; Scope
Finding: Local SQLite stores titled/tagged project/global memory. Memory MCP server and CLI provide retrieval/storage; setup wires compatible agents, Pi uses CLI/skill instead.
Retrieved: 2026-11-08

## ai-devkit:ACC-06

Finding: Unified config reconciles per-agent instructions/skills/MCP setup; compatible agents receive memory-server wiring.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/6-memory.md
Locator: How it works; MCP; CLI; Scope
Finding: Local SQLite stores titled/tagged project/global memory. Memory MCP server and CLI provide retrieval/storage; setup wires compatible agents, Pi uses CLI/skill instead.
Retrieved: 2026-11-08

## ai-devkit:PLAN-02

Finding: Lifecycle skill writes requirements/design/planning/implementation/testing files under docs/ai and requires staged review by instruction.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

## ai-devkit:PLAN-04

Finding: Local SQLite memory supports titled/tagged/scope records through MCP and CLI, retrieved when relevant.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/6-memory.md
Locator: How it works; MCP; CLI; Scope
Finding: Local SQLite stores titled/tagged project/global memory. Memory MCP server and CLI provide retrieval/storage; setup wires compatible agents, Pi uses CLI/skill instead.
Retrieved: 2026-11-08

## ai-devkit:PLAN-05

Finding: Memory retrieval supplies prior project knowledge on demand. This is not a full code index.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/6-memory.md
Locator: How it works; MCP; CLI; Scope
Finding: Local SQLite stores titled/tagged project/global memory. Memory MCP server and CLI provide retrieval/storage; setup wires compatible agents, Pi uses CLI/skill instead.
Retrieved: 2026-11-08

## ai-devkit:PLAN-06

Finding: The optional first-party task-manager plugin provides persistent independent tasks, statuses, phases, blockers, evidence, artifacts, ownership and event history through ai-devkit task.

Verification: sourced
Checked: 2026-11-13
Scheduled recheck: 2027-03-13
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Source inspection covers the scoped release only. Unanswered atomic questions remain unknown; no live scenario was run.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/packages/task-manager/README.md
Locator: CLI and Storage; src/command.ts; src/database/migrations/001_initial.sql tasks and task_events
Finding: The official installable task-manager plugin adds ai-devkit task create/list/show/update/status/progress/assign/note/close commands. Stable independent task IDs, metadata and append-only events persist in tasks.db, separate from agent sessions.
Retrieved: 2026-11-13

## ai-devkit:PLAN-08

Finding: Lifecycle skill persists requirements/design/plans in repo Markdown; no server-enforced spec-drift gate established.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

## ai-devkit:COORD-01

Finding: Several agents can run in separate managed sessions and be supervised together.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/13-agent-console.md
Locator: Prerequisites; Start a Managed Agent; Hotkeys; Send a Message
Finding: Interactive TTY console lists agents, previews transcripts, starts/renames/kills agents and connects channels. Named managed start types include Claude, Codex, Gemini CLI, Grok CLI, OpenCode and Pi. Durable mode limited to Claude/Codex/Pi; managed runtime tmux or configured Herdr.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/17-multi-agent-orchestration.md
Locator: Lead vs console; Layout; Skills; Start-then-assign; Known limitations
Finding: Product orchestration skill guides a lead using agent start/send/list to supervise named workers and cross-harness review. Users manually supply separate worktree directories; same-folder session matching may collide. Console experimental on macOS/Linux and unsupported Windows.
Retrieved: 2026-11-08

## ai-devkit:COORD-02

Finding: Lead uses named workers and start-then-assign handshake; same-folder session detection collisions are documented.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/17-multi-agent-orchestration.md
Locator: Lead vs console; Layout; Skills; Start-then-assign; Known limitations
Finding: Product orchestration skill guides a lead using agent start/send/list to supervise named workers and cross-harness review. Users manually supply separate worktree directories; same-folder session matching may collide. Console experimental on macOS/Linux and unsupported Windows.
Retrieved: 2026-11-08

## ai-devkit:COORD-03

Finding: AI DevKit orchestration skills equip a lead to start, message, inspect and wait for workers across harnesses.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/17-multi-agent-orchestration.md
Locator: Lead vs console; Layout; Skills; Start-then-assign; Known limitations
Finding: Product orchestration skill guides a lead using agent start/send/list to supervise named workers and cross-harness review. Users manually supply separate worktree directories; same-folder session matching may collide. Console experimental on macOS/Linux and unsupported Windows.
Retrieved: 2026-11-08

## ai-devkit:COORD-04

Finding: The scoped CLI/daemon and official plugin set has no schedule or external-event service that starts agent runs. A daemon discovery sweep only refreshes session state.

Verification: sourced
Checked: 2026-11-13
Scheduled recheck: 2027-03-13
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Source inspection covers the scoped release only. Unanswered atomic questions remain unknown; no live scenario was run.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/rust/crates/devkitd/src/server.rs
Locator: UnixListener; dispatcher method/CLI/plugin inventory; packages/cli/src/tui/console; shipped task-manager commands; searched cron, schedules, webhooks, roles, SAML, OIDC, diff renderer and PR creation across product code
Finding: The scoped daemon serves local Unix-socket agent RPCs; CLI commands and shipped plugins contain no schedule/webhook service that starts work, human membership/role or enterprise SSO model. Console preview renders conversation Markdown rather than a proposed-code diff viewer; Git/PR references in task records are metadata, without PR creation/management commands.
Retrieved: 2026-11-13

## ai-devkit:COORD-05

Finding: Console messages or Telegram/Slack bridge can steer running agents; managed kill requires confirmation.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/13-agent-console.md
Locator: Prerequisites; Start a Managed Agent; Hotkeys; Send a Message
Finding: Interactive TTY console lists agents, previews transcripts, starts/renames/kills agents and connects channels. Named managed start types include Claude, Codex, Gemini CLI, Grok CLI, OpenCode and Pi. Durable mode limited to Claude/Codex/Pi; managed runtime tmux or configured Herdr.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/12-channel.md
Locator: How it works; Telegram/Slack authorization
Finding: Bridge forwards messages to running terminal agents and polls output. Telegram restricts each session to first user. Slack proof of concept allows workspace members who can DM the app to send to same connected agent; responses route to first DM until restart.
Retrieved: 2026-11-08

## ai-devkit:COORD-07

Finding: Composable lifecycle/verification/orchestration skills guide workflows without prescribing one fixed agent.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/17-multi-agent-orchestration.md
Locator: Lead vs console; Layout; Skills; Start-then-assign; Known limitations
Finding: Product orchestration skill guides a lead using agent start/send/list to supervise named workers and cross-harness review. Users manually supply separate worktree directories; same-folder session matching may collide. Console experimental on macOS/Linux and unsupported Windows.
Retrieved: 2026-11-08

## ai-devkit:RUN-01

Finding: The local CLI/daemon runs agents on its own macOS/Linux host, including a user-controlled always-on Linux server reached by SSH. systemd user persistence survives logout; this does not keep a sleeping execution host running.

Verification: sourced
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/16-runtime.md
Locator: Runtime; Commands; Upgrade
Finding: Rust devkitd auto-spawns over Unix socket, logs locally and supports Linux systemd user persistence; daemon registry/persistence is local.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/rust/crates/devkitd/src/runtime.rs
Locator: Runtimes and StartInput; runtime/tmux.rs and herdr.rs; web/content/docs/16-runtime.md Linux persistence; orchestration guide manual git worktree setup
Finding: The complete runtime bundle launches agents through tmux or Herdr on the daemon host. The local Unix-socket control plane can run on a user-controlled Linux server and systemd keeps it alive after logout; no vendor service is required. It has no automatic worktree provisioning, container isolation or VM runtime.
Retrieved: 2026-11-13

## ai-devkit:RUN-02

Finding: Worktree setup is manual guidance: users create directories and pass --cwd. The scoped runtime bundle supplies terminal processes without product-owned container or VM isolation.

Verification: sourced
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/17-multi-agent-orchestration.md
Locator: Lead vs console; Layout; Skills; Start-then-assign; Known limitations
Finding: Product orchestration skill guides a lead using agent start/send/list to supervise named workers and cross-harness review. Users manually supply separate worktree directories; same-folder session matching may collide. Console experimental on macOS/Linux and unsupported Windows.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/19-permissions.md
Locator: Summary matrix; Per-harness presets
Finding: Linux 0.70.1 guidance configures underlying harness allow-lists/trust, with broad shell/file permissions. Other harnesses need verification. This is not an AI DevKit security sandbox.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/rust/crates/devkitd/src/runtime.rs
Locator: Runtimes and StartInput; runtime/tmux.rs and herdr.rs; web/content/docs/16-runtime.md Linux persistence; orchestration guide manual git worktree setup
Finding: The complete runtime bundle launches agents through tmux or Herdr on the daemon host. The local Unix-socket control plane can run on a user-controlled Linux server and systemd keeps it alive after logout; no vendor service is required. It has no automatic worktree provisioning, container isolation or VM runtime.
Retrieved: 2026-11-13

## ai-devkit:RUN-03

Finding: Managed durable mode is limited to Claude/Codex/Pi; daemon persistence can be installed on Linux. No full worker crash/reboot recovery test was run.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/13-agent-console.md
Locator: Prerequisites; Start a Managed Agent; Hotkeys; Send a Message
Finding: Interactive TTY console lists agents, previews transcripts, starts/renames/kills agents and connects channels. Named managed start types include Claude, Codex, Gemini CLI, Grok CLI, OpenCode and Pi. Durable mode limited to Claude/Codex/Pi; managed runtime tmux or configured Herdr.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/16-runtime.md
Locator: Runtime; Commands; Upgrade
Finding: Rust devkitd auto-spawns over Unix socket, logs locally and supports Linux systemd user persistence; daemon registry/persistence is local.
Retrieved: 2026-11-08

## ai-devkit:RUN-05

Finding: send --wait supports timeout and readiness handshake; quotas are readings, not enforced spend limits.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/17-multi-agent-orchestration.md
Locator: Lead vs console; Layout; Skills; Start-then-assign; Known limitations
Finding: Product orchestration skill guides a lead using agent start/send/list to supervise named workers and cross-harness review. Users manually supply separate worktree directories; same-folder session matching may collide. Console experimental on macOS/Linux and unsupported Windows.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/15-capacity.md
Locator: Status; Capacity
Finding: Readiness checks are hints, not successful login probes. Capacity reads stored provider credentials and reports quota windows, availability and reset times; it does not establish task billing.
Retrieved: 2026-11-08

## ai-devkit:RUN-06

Finding: Console shows last-observed running/waiting/idle/unknown status and transcripts; status readiness is explicitly a hint.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/13-agent-console.md
Locator: Prerequisites; Start a Managed Agent; Hotkeys; Send a Message
Finding: Interactive TTY console lists agents, previews transcripts, starts/renames/kills agents and connects channels. Named managed start types include Claude, Codex, Gemini CLI, Grok CLI, OpenCode and Pi. Durable mode limited to Claude/Codex/Pi; managed runtime tmux or configured Herdr.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/15-capacity.md
Locator: Status; Capacity
Finding: Readiness checks are hints, not successful login probes. Capacity reads stored provider credentials and reports quota windows, availability and reset times; it does not establish task billing.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/16-runtime.md
Locator: Runtime; Commands; Upgrade
Finding: Rust devkitd auto-spawns over Unix socket, logs locally and supports Linux systemd user persistence; daemon registry/persistence is local.
Retrieved: 2026-11-08

## ai-devkit:RUN-07

Finding: Capacity reports provider quota windows and reset times. It does not establish per-task billed cost.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/15-capacity.md
Locator: Status; Capacity
Finding: Readiness checks are hints, not successful login probes. Capacity reads stored provider credentials and reports quota windows, availability and reset times; it does not establish task billing.
Retrieved: 2026-11-08

## ai-devkit:TEAM-01

Finding: Slack proof-of-concept bridge permits multiple workspace members to send text toward one agent; Telegram allows only first user per bridge session.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/12-channel.md
Locator: How it works; Telegram/Slack authorization
Finding: Bridge forwards messages to running terminal agents and polls output. Telegram restricts each session to first user. Slack proof of concept allows workspace members who can DM the app to send to same connected agent; responses route to first DM until restart.
Retrieved: 2026-11-08

## ai-devkit:TEAM-02

Finding: The scoped application uses local OS-account state and chat-service bridge authorization. It has no named human workspace roles or enterprise SSO.

Verification: sourced
Checked: 2026-11-13
Scheduled recheck: 2027-03-13
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Source inspection covers the scoped release only. Unanswered atomic questions remain unknown; no live scenario was run.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/rust/crates/devkitd/src/server.rs
Locator: UnixListener; dispatcher method/CLI/plugin inventory; packages/cli/src/tui/console; shipped task-manager commands; searched cron, schedules, webhooks, roles, SAML, OIDC, diff renderer and PR creation across product code
Finding: The scoped daemon serves local Unix-socket agent RPCs; CLI commands and shipped plugins contain no schedule/webhook service that starts work, human membership/role or enterprise SSO model. Console preview renders conversation Markdown rather than a proposed-code diff viewer; Git/PR references in task records are metadata, without PR creation/management commands.
Retrieved: 2026-11-13

## ai-devkit:TEAM-03

Finding: Underlying harness permissions/trust must be configured; tested presets are Linux 0.70.1 guidance with broad access.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/19-permissions.md
Locator: Summary matrix; Per-harness presets
Finding: Linux 0.70.1 guidance configures underlying harness allow-lists/trust, with broad shell/file permissions. Other harnesses need verification. This is not an AI DevKit security sandbox.
Retrieved: 2026-11-08

## ai-devkit:SHIP-01

Finding: Phase Markdown and historical transcripts remain available locally; output can be piped into agent send. The product console has no dedicated code-change diff review view.

Verification: sourced
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/13-agent-console.md
Locator: Prerequisites; Start a Managed Agent; Hotkeys; Send a Message
Finding: Interactive TTY console lists agents, previews transcripts, starts/renames/kills agents and connects channels. Named managed start types include Claude, Codex, Gemini CLI, Grok CLI, OpenCode and Pi. Durable mode limited to Claude/Codex/Pi; managed runtime tmux or configured Herdr.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/rust/crates/devkitd/src/server.rs
Locator: UnixListener; dispatcher method/CLI/plugin inventory; packages/cli/src/tui/console; shipped task-manager commands; searched cron, schedules, webhooks, roles, SAML, OIDC, diff renderer and PR creation across product code
Finding: The scoped daemon serves local Unix-socket agent RPCs; CLI commands and shipped plugins contain no schedule/webhook service that starts work, human membership/role or enterprise SSO model. Console preview renders conversation Markdown rather than a proposed-code diff viewer; Git/PR references in task records are metadata, without PR creation/management commands.
Retrieved: 2026-11-13

## ai-devkit:SHIP-02

Finding: verify/TDD/review skills instruct fresh verification before completion; no independent runtime-enforced gate was established.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

## ai-devkit:SHIP-03

Finding: Shipped guides can instruct an agent to use Git and manually created worktrees. The scoped CLI/plugin implementation has no product-owned PR creation or management workflow.

Verification: sourced
Checked: 2026-11-13
Scheduled recheck: 2027-03-13
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Source inspection covers the scoped release only. Unanswered atomic questions remain unknown; no live scenario was run.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/rust/crates/devkitd/src/server.rs
Locator: UnixListener; dispatcher method/CLI/plugin inventory; packages/cli/src/tui/console; shipped task-manager commands; searched cron, schedules, webhooks, roles, SAML, OIDC, diff renderer and PR creation across product code
Finding: The scoped daemon serves local Unix-socket agent RPCs; CLI commands and shipped plugins contain no schedule/webhook service that starts work, human membership/role or enterprise SSO model. Console preview renders conversation Markdown rather than a proposed-code diff viewer; Git/PR references in task records are metadata, without PR creation/management commands.
Retrieved: 2026-11-13

## ai-devkit:OWN-01

Finding: AI DevKit application source is Apache-2.0 licensed.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/LICENSE
Locator: Apache License Version 2.0
Finding: Application repository source is Apache-2.0 licensed.
Retrieved: 2026-11-08

## ai-devkit:OWN-02

Finding: Core CLI/daemon, memory and console run on user-controlled machine; no hosted service required.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/16-runtime.md
Locator: Runtime; Commands; Upgrade
Finding: Rust devkitd auto-spawns over Unix socket, logs locally and supports Linux systemd user persistence; daemon registry/persistence is local.
Retrieved: 2026-11-08

## ai-devkit:OWN-03

Finding: README explicitly says no telemetry and local memory. Channel tokens are local plaintext files mode 0600; agent/provider terms remain separate.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-12-08
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/README.md
Locator: Start in 30 seconds; Operate agents; Memory; Workflows; Boundaries
Finding: Local-first control layer offers unified configuration, console, cross-agent messages, local SQLite memory and composable lifecycle/verification skills. It explicitly is not a hosted service, has no telemetry and does not run remote cloud agents.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/12-channel.md
Locator: How it works; Telegram/Slack authorization
Finding: Bridge forwards messages to running terminal agents and polls output. Telegram restricts each session to first user. Slack proof of concept allows workspace members who can DM the app to send to same connected agent; responses route to first DM until restart.
Retrieved: 2026-11-08

## ai-devkit:OWN-04

Finding: AI DevKit is free (Apache-2.0) and not a hosted service; no paid plan found, and the agents/models it coordinates are paid separately to their providers. The managed Gemini CLI worker can use a user-supplied Google API key, so provider model usage can be paid through the user’s own key.

Verification: sourced
Checked: 2026-11-10
Scheduled recheck: 2026-11-24
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: First-party pricing sources read 2026-11-10

First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
Provider credentials and model usage are separate from the free ADE application; no billing test ran.

Source: https://ai-devkit.com/
Locator: Install section, line under install command
Finding: The site says AI DevKit is free and Apache-2.0 licensed.
Retrieved: 2026-11-10

Source: https://github.com/codeaholicguy/ai-devkit/blob/main/README.md
Locator: 'Not a hosted service' bullet; License section
Finding: The README says it is not a hosted service, runs locally and coordinates agents the user already uses.
Retrieved: 2026-11-10

Source: https://github.com/codeaholicguy/ai-devkit/blob/main/LICENSE
Locator: Apache License 2.0, section 2 (Grant of Copyright License)
Finding: The Apache-2.0 license grants a perpetual, no-charge, royalty-free copyright licence to use and redistribute the software.
Retrieved: 2026-11-10

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/19-permissions.md
Locator: Summary matrix Gemini CLI login-free option; Gemini CLI worker setup and orchestration references.
Finding: The official ai-devkit orchestration guide explicitly lists Google API-key authentication as an alternative to login for the managed Gemini CLI worker. The application orchestrates agents authenticated to users’ own providers; it does not supply a bundled model quota.
Retrieved: 2026-11-13

## ai-devkit:OWN-06

Finding: Latest listed CLI release 0.72.0 was published November 3; console remains experimental macOS/Linux and unsupported Windows.

Verification: agent-cross-checked
Checked: 2026-11-08
Scheduled recheck: 2026-11-22
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Only the named facts are documented. Unanswered atomic questions remain unknown; no execution test was performed.

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/docs/17-multi-agent-orchestration.md
Locator: Lead vs console; Layout; Skills; Start-then-assign; Known limitations
Finding: Product orchestration skill guides a lead using agent start/send/list to supervise named workers and cross-harness review. Users manually supply separate worktree directories; same-folder session matching may collide. Console experimental on macOS/Linux and unsupported Windows.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/blob/99ac1c1864749daa5b1387ad16215ff9b0eb08d9/web/content/roadmap/10-agent-management.md
Locator: Completed milestone; Future work
Finding: Agent management milestone complete. Future parity, ergonomics and platform hardening are not dated release promises.
Retrieved: 2026-11-08

Source: https://github.com/codeaholicguy/ai-devkit/releases/tag/cli%400.72.0
Locator: Release date and release notes
Finding: 0.72.0 was published 2026-11-03. Release notes describe the scoped changes; this is not a hands-on check.
Retrieved: 2026-11-08

## ai-devkit:OWN-08

Finding: AI DevKit is free Apache-2.0 software run locally through npx, with no paid plan or hosted service. The coding agents it supervises are paid to their providers.

Verification: agent-cross-checked
Checked: 2026-11-10
Scheduled recheck: 2026-11-24
Plan: Not specified
Surface: AI DevKit CLI, experimental agent console and devkitd
Version: Source documentation at 99ac1c1864749daa5b1387ad16215ff9b0eb08d9

Free scenarios, usage caps and card requirements for the underlying agents were not checked. No installed-product test was run.

Source: https://github.com/codeaholicguy/ai-devkit/blob/6ddfed6354e8634e39289ac203252a7777bfc3cb/LICENSE#L1-L3
Locator: LICENSE lines 1-3, commit 6ddfed6
Finding: The repository is licensed under the Apache License, Version 2.0.
Retrieved: 2026-11-10

Source: https://github.com/codeaholicguy/ai-devkit/blob/6ddfed6354e8634e39289ac203252a7777bfc3cb/README.md#L18-L24
Locator: README.md setup commands (lines 18-24) and 'Not a hosted service' (line 249), commit 6ddfed6
Finding: AI DevKit is run free with npx ai-devkit@latest setup and init; the README says it is Apache-2.0, runs locally and is not a hosted service, and names no price or paid plan.
Retrieved: 2026-11-10