Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.
1
Prepare the server locally
Run this once before adding it to Claude Code.
git clone https://github.com/quentintou/agent-board.git
cd agent-board
npm install
npm run build
npm start2
Register it in Claude Code
claude mcp add agent-board -- node /path/to/agent-board/dist/index.jsReplace any placeholder paths in the command with the real path on your machine.
3
Make your agent remember this setup
agent-board's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Kanban dashboard with 6 workflow columns
- DAG dependencies to enforce task execution order
- Automated task retries for failed items
- Task chaining for building automated pipelines
- Real-time webhook notifications for agent coordination
Tools 3
create_taskCreates a new task on the board.move_taskMoves a task to a different column.add_commentAdds a comment to a task thread.Try it
→Create a new task titled 'Research competitor pricing' and add it to the backlog.
→Move task ID 101 to the 'doing' column.
→Add a comment to task 101 saying 'I have started the research phase'.
→List all tasks currently in the 'todo' column.
Original README from quentintou/agent-board
<h1 align="center">🎯 Agent Board</h1>
<strong>Multi-agent task orchestration for OpenClaw and AI agent teams.</strong>
Kanban dashboard · REST API · MCP server · DAG dependencies · Auto-retry · Audit trail
Features •
Quick Start •
OpenClaw Integration •
API •
MCP •
Dashboard •
Architecture
Why Agent Board?
Running multiple AI agents without coordination is chaos. Each agent works in isolation, tasks get duplicated, failures go unnoticed, and there's no way to build multi-step workflows.
Agent Board fixes this. It's a task management system purpose-built for AI agent teams — whether you're running OpenClaw agents, Claude, or any LLM-based agents.
- Agents pick up work from the board via heartbeat polling or webhook notifications
- Dependencies are enforced — Agent B can't start until Agent A finishes
- Failed tasks auto-retry — no human intervention for transient failures
- Task chaining builds pipelines — when one agent finishes, the next one starts automatically
- Full audit trail — know exactly who did what, when, and why
- MCP native — agents interact through Model Context Protocol tools
Works standalone or as the orchestration layer for an OpenClaw multi-agent setup.
Features
| Feature | Description |
|---|---|
| Kanban Board | 6 columns: backlog → todo → doing → review → done → failed |
| DAG Dependencies | Tasks can depend on other tasks. Moving to doing is blocked until all dependencies are done. Cycle detection prevents deadlocks. |
| Quality Gates | Mark tasks as requiresReview: true — they must pass through review before done. |
| Auto-Retry | When a task moves to failed, it automatically retries (back to todo) up to maxRetries times. System comments track each attempt. |
| Task Chaining | Define a nextTask on any task. When it completes, the next task is auto-created and assigned. Build pipelines without orchestration code. |
| Real-Time Communication | Task comment threads for agent-to-agent discussion. Webhooks fire on every event (comment, assign, move) — agents wake in seconds, not minutes. |
| HMAC-SHA256 Signing | All outbound webhooks are cryptographically signed. Receiving agents can verify message authenticity. Includes timestamp for replay protection. |
| OpenClaw Webhooks | Native OpenClaw webhook integration to wake agents when tasks are assigned, retried, or chained. |
| Audit Trail | Every action is logged to audit.jsonl — who did what, when, to which task. Queryable via API. Both REST and MCP mutations are tracked. |
| Client View | Read-only project dashboard for external stakeholders. Enable per-project with clientViewEnabled. Hides agent names and internal details. |
| Project Templates | Pre-define task sets as JSON templates. Apply them to any project in one call. |
| Board Stats | Per-agent and global statistics: completion rates, average duration, stuck task detection. |
| MCP Server | Full Model Context Protocol server — AI agents manage tasks through 12 MCP tools. Compatible with Claude Desktop, Claude Code, and any MCP client. |
| API Key Auth | Optional per-agent API key authentication. Backward-compatible (no keys = no auth). |
| Zod Validation | All inputs validated with Zod schemas. Clear error messages on invalid requests. |
| Concurrent Safety | Per-file async mutex locking on all writes. Atomic temp-file-then-rename. No corruption under concurrent access. |
| Auto-Backup | Automatic backups before every write (up to 50 per file, auto-pruned). |
Quick Start
git clone https://github.com/quentintou/agent-board.git
cd agent-board
npm install
npm run build
npm start
Open http://localhost:3456 for the Kanban dashboard, or hit http://localhost:3456/api for the REST API.
Options
node dist/index.js --port 8080 --data ./my-data
| Flag | Default | Descr