ClawTeam Multi-Agent Coordination
ClawTeam Multi-Agent Coordination
ClawTeam is a framework-agnostic CLI tool for coordinating multiple AI agents as a team. It provides file-based team management, inter-agent messaging, shared task tracking with dependency resolution, plan approval workflows, and terminal-based monitoring dashboards.
All operations are performed via the clawteam CLI. Data is stored in ~/.clawteam/ by default.
Core Concepts
Teams — A named group of agents with one leader and zero or more workers. Created via
clawteam team spawn-team. The leader approves joins, reviews plans, and coordinates shutdown.
Inbox — File-based message queue per agent. inbox send for point-to-point, inbox broadcast
for all members. inbox receive consumes messages (destructive); inbox peek reads without consuming.
Tasks — Shared task board with statuses: pending, in_progress, completed, blocked.
Tasks support dependency chains (--blocks, --blocked-by). Completing a task auto-unblocks dependents.
More from win4r/clawteam-openclaw
clawteam
Multi-agent swarm orchestration. USE THIS (not delegate_task) when the user says team/swarm/multi-agent/clawteam/parallel-agents/agent-team, or asks for multi-perspective analysis (stocks, research, code review, strategy). Spawns N Hermes workers in tmux windows with git worktree isolation, file-based inboxes, and a kanban board. Four built-in templates: hedge-fund (7 analyst agents), research-paper, code-review, strategy-room.
11clawteam-dev
>
7