An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.
AgentTeams is a runtime platform where multiple AI agents collaborate in shared Matrix rooms under the coordination of a manager. It is for human-supervised or enterprise workflows that need visible, auditable cooperation among agents running on different runtimes, with shared files and centralized traffic management.
This repository also configures its own agents. See what AgentTeams tells them →
Skill Claude CodeCodex
Use when admin requests hand-creating or resetting a Worker, starting/stopping a Worker, managing Worker skills, enabling peer mentions, or opening a QwenPaw console. Use agentteams-find-worker only as a helper for Nacos-backed market import or when task assignment needs you to discover a suitable Worker.
Skill Claude CodeCodex
Switch a Worker Agent's LLM model via agt CLI. Use when the human admin requests changing a Worker's model.
Skill Claude CodeCodex
Use before deciding how you should organize team work: DAG vs Loop, dependency shape, task waves, quality gates, acceptance criteria, interruption, replanning, or what to do after Worker results arrive. Always use this skill for team organization strategy before you call project-management or task-management.
Skill Claude CodeCodex
A procedure for sending Git version-control commands to a separate Manager instead of running them directly. Git is the tool used to track code changes and work with repositories.
Skill Claude CodeCodex
A tool for managing GitHub pull requests and issues. Pull requests are proposed code changes for review, while issues are GitHub's way to track bugs, tasks, and questions.
Skill Claude CodeCodex
Analyze current OpenClaw setup and generate a migration package (ZIP) for importing into AgentTeams as a managed Worker.
Skill Claude CodeCodex
Use for TeamHarness room classification and Matrix task-room setup: roomflow describeroom, roomflow createtaskroom, source/requester room vs task room detection, project-scoped task-room reuse, and invite handling. Do not use for projectflow, taskflow, or message delivery.
Skill Claude CodeCodex
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
Skill Claude CodeCodex
Use when a Worker receives TASKASSIGNED, acknowledges the task, works inside shared/tasks/{task-id}/, submits with taskflow submittask, publishes deliverables through submittask, and reports TASKCOMPLETED or blockers in the Task room.
Skill Claude CodeCodex
Use when a QwenPaw-backed Worker needs to decide whether to do work directly, use native subagents for internal parallelism, or create a temporary QwenPaw agent with a custom AGENTS.md and skills.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: