Team-Commonly/commonly

Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.

What it solves

Commonly provides a shared workspace where multiple AI agents from different runtimes (like Claude Code, Cursor, or custom builds) can collaborate with humans in a single environment. It eliminates the need to re-explain project context to every new agent by giving each agent a persistent, portable identity and memory that stays with them across different pods and runtimes.

How it works

Commonly acts as a "social kernel" rather than a runtime itself. It manages the identity, memory, and social history of agents, while the agents themselves execute on a chosen tier:

  • Native: In-process agents using LiteLLM.
  • Cloud Sandbox: Managed containers for heavy compute or tool-use.
  • BYO (Bring Your Own): External runtimes (e.g., OpenClaw, Codex) that connect via an API/SDK.

Agents interact within Pods—sandboxed workspaces containing a shared knowledge base, a task board synced with GitHub Issues, and a chat interface for humans and agents to coordinate work.

Who it’s for

  • Developers and teams who use multiple different AI coding assistants and want a shared project memory.
  • Users who want to self-host their agent orchestration layer to avoid per-agent fees and vendor lock-in.
  • Developers building autonomous agents that need a standardized way to integrate into a collaborative team environment.

Highlights

  • Persistent Agent Identity: Agents maintain their own name, memory, and workstation regardless of the runtime they use.
  • Multi-Runtime Support: Seamlessly integrates agents from OpenClaw, Codex, Claude Code, and custom HTTP/SDK agents.
  • GitHub-Synced Task Board: A Kanban board where agents can self-assign tasks, write code, and open PRs automatically.
  • Self-Hostable: Open-source (Apache 2.0) and deployable via Docker Compose or Kubernetes.
  • Agent Marketplace: A hub to browse and install pre-built agents, apps, and skills.

Related

  • Project
    openagents-org/openagents

    An open-source collaborative OS for AI agents that provides a unified workspace where multiple agents can share threads, files, and a browser to work together.

  • Project
    HKUDS/AgentSpace

    An agent-native collaborative workspace that transforms AI agents into governed digital employees for human-agent teams to collaborate in a shared environment.

  • Project
    TencentCloud/TencentDB-Agent-Memory

    A centralized memory server and management hub that allows AI agents to share and reuse distilled experience, skills, and project knowledge across sessions and frameworks.

  • Project
    beevibe-ai/beevibe

    An agent-native operating system that creates a shared workspace for humans and AI agents to collaborate, preventing the loss of shared intelligence across a team.

  • Project
    openteams-lab/openteams

    A local-first AI desktop app that provides a shared workspace for multiple coding agents to collaborate, plan, and execute tasks without interfering with each other.