by clawwork-ai
Client for OpenClaw — Connect ClawWork to your own OpenClaw and unlock 10x multi-session productivity.
# Add to your Claude Code skills
git clone https://github.com/clawwork-ai/ClawWorkLast scanned: 5/16/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-16T06:21:37.888Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}ClawWork is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by clawwork-ai. Client for OpenClaw — Connect ClawWork to your own OpenClaw and unlock 10x multi-session productivity. It has 521 GitHub stars.
Yes. ClawWork passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/clawwork-ai/ClawWork" and add it to your Claude Code skills directory (see the Installation section above).
ClawWork is primarily written in TypeScript. It is open-source under clawwork-ai on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh ClawWork against similar tools.
No comments yet. Be the first to share your thoughts!
English · 简体中文 · 繁體中文 · 日本語 · 한국어
The local-first workspace for the Agent OS era.
Desktop client for OpenClaw — run agent tasks in parallel, keep artifacts durable, and find your files later.
Download · PWA · Quick start · Teams · What you get · Data & architecture · Repo layout · Roadmap · Contributing · Keynote
⚠️ Official Repository This is the official ClawWork project: https://github.com/clawwork-ai/clawwork
A copycat repository (ClawWorkAi/ClawWork) and website (clawworkai.store) have been found without proper attribution. Please be aware and use the official links above.
Official Website: https://clawwork-ai.github.io/ClawWork/
Agents are multiplying. The bottleneck is no longer capability — it's the operator surface.
As agent runtimes proliferate, users end up juggling sessions across chat windows, web UIs, and terminals, each with its own context and no shared memory. Just as IDEs became the operator layer for code and terminals for Unix, the Agent OS needs a workspace layer. ClawWork is building that layer — starting as the best-in-class client for OpenClaw, extensible toward a multi-runtime future.
OpenClaw is powerful. Plain chat is a bad container for the kind of work it can do.
Once you have multiple sessions, long-running jobs, approval stops, generated files, recurring automation, and different gateways, chat history turns into mud. Status vanishes. Files vanish. Context vanishes.
ClawWork fixes that. Every task becomes a durable workspace with its own session, artifacts, controls, and history — laid out in a three-panel UI: tasks on the left, active work in the center, artifacts and context on the right.
The dedicated UI for OpenClaw — stop chatting with Agents in Feishu.
| Feishu / DingTalk / Slack | ClawWork | |
|---|---|---|
| Layout | Single chat thread | Three-column: task list, conversation, progress panel |
| Multi-task | One conversation at a time | Parallel tasks in isolated sessions |
| Tool calls | Hidden or text-only | Real-time visualization with expandable details |
| Artifacts | Lost in chat history | Auto-saved to local Git repo, searchable |
| Progress | No structured tracking | Step-by-step progress panel |
| Data ownership | On third-party servers | 100% local (SQLite + Git) |
Launch prep: Record a 60-second demo and save as
docs/demo.gif. See docs/promotion/demo-recording.md for the checklist.
One agent is useful. A coordinated team of agents is a workforce.
ClawWork Teams package multiple agents into a single deployable unit — roles, personalities, skills, and workflow included. A coordinator agent breaks down the task and delegates to worker agents, each running in its own sub-session. You see the full orchestration in real time.
skill → agent → team
teams/clawwork-dev/
├── TEAM.md # team metadata and workflow
└── agents/
├── manager/ # coordinator — orchestrates the team
│ ├── IDENTITY.md # role and prompt
│ ├── SOUL.md # personality and style
│ └── skills.json # skill dependencies
├── architect/ # worker — designs solutions
├── frontend-dev/ # worker — builds UI
├── core-dev/ # worker — builds core logic
└── ...
Once installed, pick a team when creating a task. The coordinator takes over from there.
brew tap clawwork-ai/clawwork
brew install --cask clawwork
Prebuilt macOS, Windows, and Linux builds are available on the Releases page. The app updates itself — new versions download in the background and install when you quit.
No install required — open cpwa.pages.dev in any modern browser. Works on desktop and mobile, installable to your home screen.
ws://127.0.0.1:18789.@ files for context, or use / commands.cron, every, or at expressions — pick from presets or write your own, check run history, trigger manually anytime (recipe examples)@ file references, voice input, watched foldersAlt+Space by default, customizable)ClawWork talks to OpenClaw through a single Gateway WebSocket connection. Each task gets its own session key for isolation, and everything lives in a local workspace directory you choose — no cloud sync, no external database.
packages/shared/ — protocol types, constants (zero deps)
packages/core/ — shared business logic: stores, services, ports
packages/desktop/
src/main/ — Electron main: gateway WS, IPC, DB, artifacts, OS