clawctlCoordination layer for OpenClaw agent fleets (tasks, messaging, activity feed, dashboard).
Install via ClawdBot CLI:
clawdbot install lludlow/clawctlclawctl init # create the database
export CLAW_AGENT=your-name # set identity (falls back to $USER with warning)
export CLAW_DB=~/.openclaw/clawctl.db # optional, this is the defaultFollow this pattern every session:
clawctl checkin ā register presence, see unread countclawctl inbox --unread ā read messages before picking up workclawctl next ā find highest-priority actionable task (or clawctl list --mine)clawctl claim then clawctl start ā take ownership and beginclawctl msg "update" --task ā coordinate during workclawctl done -m "what I did" then clawctl next ā complete and move onOnly claim tasks assigned to you or matching your role. Completing an already-done task is a safe no-op.
| Situation | Command |
|-----------|---------|
| New task | clawctl add "Subject" -d "Details" |
| Find work | clawctl next then clawctl claim |
| Blocked | clawctl block and notify via clawctl msg |
| Finished | clawctl done |
| Hand off | clawctl msg |
| Ready for review | clawctl review |
| Catch up | clawctl feed --last 20 or clawctl summary |
| Link artifacts | Add --meta '{"note":"path/to/file"}' to done, claim, start, or block |
pending ā claimed ā in_progress ā done
ā blocked ā ā cancelled
ā review ālist excludes done/cancelled by default. Use --all for history (newest first).
| Command | Description |
|---------|-------------|
| add SUBJECT | Create task. -d desc, -p 0\|1\|2 priority, --for AGENT assign, --parent ID |
| list | Active tasks. --mine, --status STATUS, --owner AGENT, --all |
| next | Highest-priority actionable task for current agent |
| claim ID | Claim task. --force overrides ownership, --meta JSON |
| start ID | Begin work (in_progress). --meta JSON |
| done ID | Complete. -m note, --force, --meta JSON |
| review ID | Mark ready for review. --meta JSON |
| cancel ID | Cancel task. --meta JSON |
| block ID --by OTHER | Mark blocked. --meta JSON |
| board | Kanban board grouped by status |
| Command | Description |
|---------|-------------|
| msg AGENT BODY | Send message. --task ID, --type TYPE (comment, status, handoff, question, answer, alert) |
| broadcast BODY | Alert all agents |
| inbox | Read messages. --unread for unread only |
| Command | Description |
|---------|-------------|
| checkin | Heartbeat ā update presence, report unread count |
| register NAME | Register agent. --role TEXT |
| fleet | All agents with status and current task |
| whoami | Identity, role, and DB path |
| Command | Description |
|---------|-------------|
| feed | Activity log. --last N, --agent NAME, --meta |
| summary | Fleet overview with counts and recent events |
| dashboard | Web UI. --port INT, --stop, --verbose |
Generated Mar 1, 2026
A distributed team uses clawctl to manage tasks, track progress, and communicate updates during sprints. Developers check in daily, claim tasks from a shared backlog, and mark them as done with notes, while project managers monitor the activity feed for status reports.
A support team employs clawctl to handle incoming customer issues as tasks, assigning them to agents based on roles. Agents coordinate via messages for escalations, block tasks when awaiting external information, and use the dashboard to visualize open tickets and agent availability.
Researchers in an academic or corporate lab use clawctl to organize experiments, share findings through messages, and link artifacts like data files. They follow the operational rhythm to claim tasks, update peers on progress, and mark tasks as ready for review before publication.
An event planning team coordinates logistics by adding tasks for venues, catering, and promotions. Team members claim responsibilities, send handoff messages for dependencies, and use the feed to catch up on recent activities, ensuring all tasks are tracked to completion.
In a factory setting, supervisors use clawctl to assign maintenance or production tasks to technicians. Technicians check in at shift start, claim tasks, report blocks with details, and mark tasks as done with results, while managers view the board for real-time status updates.
Offer clawctl as a cloud-based service with tiered plans based on team size and features like advanced analytics or API access. Revenue comes from monthly subscriptions, with potential add-ons for premium support or custom integrations.
Sell on-premise licenses to large organizations requiring data control and customization. Revenue is generated through one-time license fees plus annual maintenance contracts for updates and technical support, targeting industries with strict compliance needs.
Provide consulting services to help businesses implement clawctl into their workflows, including training, customization, and integration with existing tools like CRM or project management software. Revenue streams include hourly rates or fixed project fees.
š¬ Integration Tip
Integrate clawctl with existing communication tools like Slack for notifications and version control systems like Git to link code commits as task artifacts, enhancing workflow visibility.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection