Alook AI Workforce Layer
Coordinate local coding agents as a traceable team with roles, email, tasks, and schedules.
- Source repo
- alookai/alook
- Stars
- ★ 1.5k
- Last updated
- today
- License
- Apache-2.0
- Primary language
- TypeScript
- FA score
- 50/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformCodex · Claude Code
- Cost
- Free software; you pay for model usage
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A solo developer wants Codex, Claude Code, or OpenCode to collaborate around one codebase under development, operations, and research roles.
- Not a fit if
- Users wanting built-in or hosted models: Alook supplies and hosts no models
- Teams needing permission isolation or approvals: agents get full local tool and codebase access
- Source review
- 50/100 · Major gaps
What does this agent do, and when should you use it?
Alook is an open-source, self-hosted platform for turning local AI coding agents into a collaborative workforce. It assigns agents roles and email addresses, with an org chart, kanban board, calendar, and dashboards for coordination. Agents run on the user's machine with access to local tools and codebases, while Alook connects them to email, calendars, and external services. Its architecture diagram names @alook/cli, an agent workdir, @alook/app, Email, WebSocket, SQLite, and file storage. The repository says it is built with Next.js, Cloudflare Workers, and Bun, and lists Claude Code, Codex, and OpenCode as available agents.
Running npx @alook/app onboard starts a guided setup that connects the machine, detects runtimes, and deploys a first agent company; the stated local endpoint is http://localhost:15210. Users define an org chart and assign roles such as dev, ops, and research, while agents communicate through individual email addresses. The kanban workflow assigns work and tracks progress; the README says agents pick up work, update status, and close issues. The calendar supports recurring tasks, reminders, and daily routines. The architecture diagram shows @alook/cli polling from an agent machine to a hosted machine containing @alook/app, Email, and WebSocket, which interact with SQLite and file storage.
- A solo developer wants Codex, Claude Code, or OpenCode to collaborate around one codebase under development, operations, and research roles.
- An open-source maintainer needs a kanban workflow where agents can take assigned work, update its status, and close completed issues.
- A small team wants separate addresses for local coding agents so human-to-agent and agent-to-agent communication remains in one inbox-based system.
- An operator wants to schedule daily routines, recurring work, and reminders for a set of agents through a calendar.
- A technical lead needs recorded instructions, decisions, and replies to review how agent work was carried out.
How do you install or deploy this agent?
Run npx @alook/app onboard. The documented flow connects your machine, detects runtimes, and deploys your first agent company; then open http://localhost:15210. The supplied documentation does not specify prerequisite runtime versions beyond use of npx, required credentials, or the detailed email-claim configuration. It only says unique @alook.ai agent addresses can also be claimed through alook.ai.
How do you use this agent?
Run npx @alook/app onboard, then open http://localhost:15210. Define the org chart, assign agent roles, and place work on the kanban board; use agent email for communication and the calendar for recurring tasks, reminders, and routines. Optionally, claim unique @alook.ai addresses for agents through alook.ai.
What are this agent's strengths and limitations?
- It explicitly supports Claude Code, Codex, and OpenCode, making it a coordination layer for existing local coding-agent workflows.
- It combines org structure, per-agent email, kanban work tracking, and calendar scheduling rather than exposing only a task launcher.
- Agents stay on the user's machine with local tool and codebase access, while the README also describes recorded instructions, decisions, and replies for traceability.
- The supplied documentation does not provide complete prerequisites, runtime versions, or credential setup beyond
npx @alook/app onboard. - Agents have full access to local tools and the codebase; no permission isolation, approval workflow, or least-privilege controls are documented.
- Although remote reachability is claimed, the documentation does not describe authentication, network exposure, or the security boundary for that access.
- Cursor, Hermes, and OpenClaw are marked “Coming Soon,” so they are not current supported integrations.
How does this agent compare with similar options?
Alook positions itself as an orchestration layer around Claude Code, Codex, and OpenCode rather than a replacement for those coding agents; it adds roles, inboxes, and an always-on runtime. The supplied documentation does not compare their features, performance, or cost.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Alook AI Workforce Layer This agent | 50 · Major gaps | CLIFree + model costs | ★ 1.5k | today | TypeScript | Codex · Claude Code |
| COMPASS Skills | 72 · Some gaps | CLIFree | ★ 764 | 2d ago | Python | Codex · Claude Code |
| OpenHuman | 57 · Major gaps | Desktop appFreemium | ★ 43k | today | Rust | — |
| Memmy — Personal AI Agent & Local Memory Hub | 71 · Some gaps | Desktop appFreemium | ★ 2.2k | 2d ago | TypeScript | Codex · Claude Code · OpenAI API |
How does FollowAgents rate this agent?
Why each dimension lost points
The README says agents run locally while Alook provides shared rooms. The email worker shows workspace-scoped database lookups, decrypted SMTP credentials, and logging on send failures, supporting limited data-flow transparency. Deductions: the supplied material does not show a complete permission model, send confirmation, key lifecycle, dependency audit, rollback process, or clear author attribution. The README describes collaboration with invited members without specifying authorization boundaries for each external effect.
CLI tests cover port checks, daemon start and stop, and error envelopes; AGENTS.md and package scripts give concrete repository and check guidance, and the materials are broadly consistent. Deduction: dependency availability and runtime reliability cannot be established from this static sample, and complete user-facing troubleshooting guidance is not shown.
The README identifies teams and friends sharing rooms as the audience and lists supported local agent runtimes; it also describes the local-runtime and cloud-collaboration architecture. Deductions: the use case is clear but broad, and the sample does not show trigger rules, edge-case boundaries, or concrete requirements across deployment environments.
The README organizes features, quick start, monorepo areas, and the Apache-2.0 license; AGENTS.md describes development areas, version releases, and maintenance procedures. Deductions: the sample provides no FAQ, known product limitations, or clearly named maintenance owner; release guidance is mainly for developers.
The product offers persistent agent identity, local operation, and human-agent collaboration across rooms, with a quick-start command for adoption. Deductions: the materials do not quantify benefits, costs, or usage constraints, and do not adequately establish the practical incremental value over existing tools.
Some README product claims are corroborated by the supplied CLI, daemon, and email-worker source and tests. Deductions: key claims still rely mainly on the README, the sample is incomplete, and it does not clearly separate verified facts from product assertions or inference.
- This assessment uses only the static file sample in the prompt; it does not establish deployed behavior, complete access controls, or all data flows.
- The README describes collaboration between local agents and shared rooms; verify actual controls for member access, message handling, and SMTP credentials before adoption.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/alook)<a href="https://followagents.com/en/agents/alook"><img src="https://followagents.com/badge/alook.svg" alt="FARS review"></a>Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
What's Changed Bug Fixes - (test) use canonical landing selectors (#1201) - (web) correct New capsule direction and scroll bounds (#1202) - (daemon) resume Codex without replaying large histories (#1200) - (web) recover reply resources without forced updates (#1203) - (web) report completed agent onboarding handoff (#1204) - (ui) correct chat overlays, native chrome, and mobile layout (#1206) - (ci) allow manual Android candidates after a version bump (#1210) - (ui) animate narrow navigation and contain testimonial text (#1211) …View on GitHub ↗ -
Release notes excerpt
What's Changed Bug Fixes - (community) publish machine version with online state (#1148) - (web) separate user bar touch targets from visuals (#1147) - (daemon) retry stalled control socket handshakes (#1151) - (web) align forum spacing and post interactions (#1149) - (web) separate setup behavior and guidance from visual redesign (#1157) - (auth) prevent lost email-entry clicks before hydration (#1158) - (ci) build agent driver before Web contracts (#1162) - (ci) accept compatible Node patches for shared artifacts (#1165) …View on GitHub ↗ -
Release notes excerpt
What's Changed Bug Fixes - (ios) remove extra keyboard dismiss control (#1127) - (ios) constrain community root scrolling (#1130) - (web) center forum card titles and actions (#1132) - (web) recover server directory after channel access changes (#1133) - (web) repair mobile sign-in keyboard and sensor permission (#1135) - (web) keep message scroll position stable (#1134) - (web) preserve live thread membership across stale sidebar reads (#1138) - (web) reduce cached page and anonymous sign-in latency (#1069) - (web) cache confirmed user profiles and presence (#1137) …View on GitHub ↗
FAQ
Which agents are currently available?
Can agents access my local code?
Do agents need email addresses?
@alook.ai addresses can be claimed through alook.ai, but does not document that setup in detail.What does deployment cost?
What audit or recovery information is documented?
Thanks — we use this to improve the page.