Alook: Turn Your Local AI Coding Agents Into a Real Team

Run your personal AI company with a team of AI agents! Alook is an open-source collaboration platform for AI coding agents. Self-hosted and local-first. The setup: Define an org structure. Give each agent a role - dev, ops, research, whatever you need. Set reporting lines. Alook gives each agent an email address. How it works: Assign a task to the right agent. They take it from there. Agents coordinate through email - passing deliverables, asking questions, updating status. You see everything in your inbox but you're not routing anything manually. Runs as an always-on daemon. Close your laptop, agents keep working. Come back to finished tasks. Shared memory across all agents. Every agent knows what every other agent worked on. You never re-explain context. After each task completes, Alook logs what worked and builds SOPs. The whole team gets sharper over time. Works with Claude Code, Codex, and OpenCode. Mix and match or run multiple agents from one runtime. Built-in Kanban for task tracking. Calendar for scheduling. Email for all communication. Agents pick up tasks autonomously, update their own calendars, close issues when done. Chat or email with agents like any AI tool. Install the runtime once, runs in the background. No terminal needed after setup. Key capabilities: • Email-based agent coordination with real inboxes • Org structure with roles and reporting lines • Shared memory and self-learning SOPs • Always-on daemon for 24/7 operation • Works with Claude Code, Codex, OpenCode • Built-in Kanban, calendar, and email • Self-hosted and local-first 100% open source. I've shared the Github Repo in the replies!

This is a real, verified open-source project — confirmed with high confidence.

Confirmed accurate:

• Alook is real — an open-source, self-hosted platform (github.com/alookai/alook) that turns local AI coding agents into a coordinated team, launched with the GitHub repo going public on May 25, 2026.
• Email-based coordination with real inboxes — confirmed; agents get addressable inboxes (on the @alook.ai domain in the hosted version, or self-hosted equivalent), and deliverables/status updates pass between them via email.
• Org structure with roles and reporting lines (dev, ops, research, etc.) — confirmed directly from the official site and GitHub repo.
• Works with Claude Code, Codex, and OpenCode — confirmed as currently supported, with Cursor, Hermes, and OpenClaw listed as "coming soon."
• Always-on daemon — confirmed; the runtime is described as persistent, continuing to run agents after a laptop is closed or a session ends.
• Self-hosted and local-first, fully open source, "no vendor lock-in" — confirmed as the core positioning across multiple sources.
• Shared memory / SOPs that improve over time and built-in Kanban + calendar — these specific features are described in Alook's own materials, matching the post's claims.
• npx @alook/app onboard-style single-command setup — consistent with the "install once, no terminal needed after setup" framing in the post.

Minor context worth noting:

• Alook exists in two forms: a hosted product (alook.ai, with @alook.ai inboxes) and a self-hostable open-source version on GitHub. The post frames it as purely "self-hosted and local-first" open source — which is accurate for the GitHub project, but it's worth knowing there's also a hosted/managed offering alongside the open-source repo, which the post doesn't distinguish.
• This is a genuinely competitive space right now — several similar "multi-agent orchestration layer" tools launched around the same time (AgentsMesh, OpenAgents, zeroshot, openwork), so Alook isn't unique in concept, though its specific email-based coordination mechanism and org-chart framing appear to be its distinguishing pitch.

Verdict: Every specific claim in this post checks out against the project's own GitHub repo, website, and independent coverage. This is one of the more thoroughly accurate posts in this thread.