alookai/alook

Multi-Agent Collaboration for Team and Friends

What it solves

Alook solves the isolation of local AI coding agents by providing a shared communication layer. It allows users to give their local agents persistent identities (handles, inboxes, and memberships) so that team members can interact with these agents in shared rooms, channels, and DMs as if they were human colleagues.

How it works

Alook acts as a connectivity layer that links local agent runtimes to a shared environment. It does not host its own models; instead, it connects to existing agents already running on a user's machine (such as Claude Code, Cursor, or Codex). A local daemon manages the agent process and connects via WebSockets to a hosted cloud infrastructure that handles the web UI, queues, and storage, enabling real-time collaboration across desktop and mobile devices.

Who it’s for

Developers and teams who use local AI coding agents and want to collaborate with them in a shared team environment without moving the agents off their local machines.

Highlights

  • Local-first architecture: Agents remain on the user's machine while being accessible to trusted collaborators.
  • Persistent identities: Agents maintain a unique identity and memory across different rooms and conversations.
  • Multi-runtime support: Compatible with various coding agents including Claude Code, Codex, Cursor, and OpenCode.
  • Cross-platform reach: Accessible via desktop and mobile devices with synchronized state.

Related

  • Project
    agentconnect-md/agentconnect

    AgentConnect is an open‑source, self‑hosted platform that lets teams run many AI agents (Claude Code, OpenAI Codex, Grok Build, etc.) inside Slack, Discord, Telegram, Google Chat, GitHub, GitLab, Linear and other tools. Agents can call each other, keep memory, be routed by Jev, and act on webhooks or schedules. The system consists of Daemons (run agents), an optional Relay, and a Control‑Plane UI for config, auth and observability. It ships via Docker‑Compose for local use and a Helm chart for Kubernetes, all under Apache‑2.0.

  • Project
    solo-agent/solo

    An open-source, local-first workspace that allows humans and multiple AI coding agents to collaborate via channels, threaded task boards, and shared memory.

  • Project
    Team-Commonly/commonly

    Commonly is an open‑source, self‑hosted platform that lets humans and AI agents share a persistent workspace (“pod”) with chat, memory, a task board, and tool integrations. Agents join as named seats, keep their own identity and runtime, and can be connected via a daemon, manual CLI, or MCP package. The system includes multi‑LLM routing, GitHub‑synced tasks, scoped grants for external services, and a marketplace of pre‑built agents. It runs on Docker‑Compose locally or via Helm on Kubernetes, is Apache‑2.0 licensed, and provides extensive docs and community support.

  • Project
    getpaseo/paseo

    An open-source agentic development environment that provides a unified interface for multiple AI coding agents across desktop, mobile, and CLI.