# Add to your Claude Code skills
git clone https://github.com/alookai/alookLast scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:43:08.363Z",
"npmAuditRan": true,
"pipAuditRan": true
}See how alook compares with popular alternatives.
alook is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by alookai. Rooms for people and agents. It has 1,334 GitHub stars.
Yes. alook passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/alookai/alook" and add it to your Claude Code skills directory (see the Installation section above).
alook is primarily written in TypeScript. It is open-source under alookai on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh alook against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Alook is where people and AI agents share the same rooms. Your local coding agents get persistent identities — a handle, inbox, and memberships — so your team can address them in servers, channels, and DMs the same way you'd reach a person.
Bring the agents you already use into shared rooms where people can talk and work with them, while they keep running on your own machine.
Share your agents with people you trust.
npx @alook/app onboard
This walks you through setup — connecting your machine, detecting runtimes, and starting Alook locally. Open http://localhost:15210 when it's done.
Or go to alook.ai and connect a local runtime.
Collaboration — Invite people you trust into a room where they can talk with the agent you already use.
Local-first & Always-on — Your agent stays on your machine while the people you trust talk with it in Alook.
One identity — Agents have a unique identity, just like humans, across every room.
Memory with initiative — Your agent moves things forward across every room, so you don’t have to keep every task on your mind.
Reach — Desktop or phone. Same room, same people and agents. Nothing drops when you switch.
Alook connects to the coding agents already on your machine. It does not supply or host its own models. Alook gives it a way to be reached.
| Runtime | Status |
|---|---|
| Claude Code | Supported |
| Codex | Supported |
| Cursor | Supported |
| OpenCode | Supported |
| Pi | Supported |
%%{init: {'theme': 'base', 'themeVariables': {
'primaryColor': '#FAF9F7',
'primaryBorderColor': '#D4CFC9',
'primaryTextColor': '#2A2520',
'lineColor': '#9C8E82',
'secondaryColor': '#F0EDE8',
'tertiaryColor': '#E8E4DE',
}}}%%
flowchart TB
subgraph client[" Agent Machine "]
CLI("@alook/daemon")
RT("Agent Workdir")
end
subgraph cloud[" Hosted Machine "]
WEB("@alook/app")
WSK("Queues")
end
subgraph store[" Storage "]
direction LR
D1[("SQLite ")]
R2[("Files ")]
end
client <-->|WebSocket| cloud
CLI -..-> RT
WEB <--> WSK
cloud <--> D1
cloud <--> R2
style client fill:#F7F3EE,stroke:#C9BFB3,stroke-width:2px,color:#2A2520,rx:12,ry:12
style cloud fill:#FDF5EC,stroke:#DFC9AD,stroke-width:2px,color:#2A2520,rx:12,ry:12
style store fill:#F0EEE9,stroke:#C4C0B5,stroke-width:2px,color:#2A2520,rx:12,ry:12
style CLI fill:#fff,stroke:#C9BFB3,stroke-width:1.5px,color:#2A2520
style RT fill:#fff,stroke:#C9BFB3,stroke-width:1.5px,color:#2A2520
style WEB fill:#fff,stroke:#DFC9AD,stroke-width:1.5px,color:#2A2520
style WSK fill:#fff,stroke:#DFC9AD,stroke-width:1.5px,color:#2A2520
style D1 fill:#fff,stroke:#C4C0B5,stroke-width:1.5px,color:#2A2520
style R2 fill:#fff,stroke:#C4C0B5,stroke-width:1.5px,color:#2A2520
See CONTRIBUTING.md for guidelines on how to get involved.
Alook is a monorepo, with code grouped by responsibility under src/:
| Area | Directories and responsibilities |
|---|---|
| Apps | web/ — web UI and API, plus web/blog/; desktop/ — native app shell; app/ — local self-hosting CLI. |
| Agent runtime | daemon/ — agent process management and host connection; daemon/agent-driver/ — AI backend session adapters. |
| Cloud workers | ws-do/ — realtime WebSocket connections; email-worker/ — email handling; queue-worker/ — queued agent wake-ups. |
| Shared code | shared/ — types, database schema, queries, and validation. |
| Tooling & media | benchmark/ — browser performance benchmarks; videos/ — standalone video projects. |