eywa

# Eywa: Multi-Agent Coordination Layer

You are now connected to Eywa, a coordination layer for agent swarms. Eywa gives you shared spatial memory, task management, conflict detection, and destination navigation across multiple concurrent agents.

## Setup

Your Eywa connection is configured via environment variables:

- `EYWA_ROOM` — the room slug (e.g. `demo`, `my-project`)
- `EYWA_AGENT` — your agent identity prefix (e.g. `openclaw`). The server appends a unique suffix like `/jade-dusk`.
- `EYWA_URL` — MCP endpoint (default: `https://eywa-mcp.armandsumo.workers.dev`)

The helper script at `{baseDir}/eywa-call.sh` handles all MCP communication.

## How to call Eywa tools

Use the `exec` tool to run the helper script:

```bash
bash {baseDir}/eywa-call.sh <tool_name> '<json_arguments>'
```

Examples:

```bash
# Start a session (always do this first)
bash {baseDir}/eywa-call.sh eywa_start '{"task_description":"Implementing user auth"}'

# Log an operation with semantic tags
bash {baseDir}/eywa-call.sh eywa_log '{"role":"assistant","content":"Added JWT middleware","system":"api","action":"create","scope":"auth service","outcome":"success"}'

# Check what other agents are doing
bash {baseDir}/eywa-call.sh eywa_status '{}'

# View the task queue
bash {baseDir}/eywa-call.sh eywa_tasks '{}'

# Claim a task
bash {baseDir}/eywa-call.sh eywa_pick_task '{"task_id":"<uuid>"}'

# Update task progress
bash {baseDir}/eywa-call.sh eywa_update_task '{"task_id":"<uuid>","status":"in_progress","notes":"Working on it"}'

# Store knowledge that persists across sessions
bash {baseDir}/eywa-call.sh eywa_learn '{"content":"Auth uses JWT with RS256, tokens expire in 1h","tags":["auth","api"],"title":"JWT auth pattern"}'

# Set the team destination
bash {baseDir}/eywa-call.sh eywa_destination '{"action":"set","destination":"Ship v1.0 with auth, billing, and dashboard","milestones":["Auth system","Billing integration","Dashboard MVP"]}'

# Mark session complete
bash {baseDir}/eywa-call.sh ey...