poco-claw

Name: poco-claw
Author: poco-ai

Verified

A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, a sandboxed runtime and channel-based team collaboration. Under the hood, it is powered by a Claude Code–based agent.

1,345stars

126forks

Python

Installation

# Add to your Claude Code skills
git clone https://github.com/poco-ai/poco-claw

Getting Started

Guides for using ai agents skills like poco-claw.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 4/29/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-04-29T06:23:49.441Z",
  "semgrepRan": false,
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

Frequently Asked Questions

What is poco-claw?

poco-claw is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by poco-ai. A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, a sandboxed runtime and channel-based team collaboration. Under the hood, it is powered by a Claude Code–based agent. It has 1,345 GitHub stars.

Is poco-claw safe to use?

Yes. poco-claw 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.

How do I install poco-claw?

Clone the repository with "git clone https://github.com/poco-ai/poco-claw" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is poco-claw written in?

poco-claw is primarily written in Python. It is open-source under poco-ai on GitHub, so you can review or fork the full source.

Are there alternatives to poco-claw?

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 poco-claw against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

apple-docs-mcp open-agent-sdk

Poco Hero

Poco: Your Pocket Coworker

A safer, more beautiful, and easier-to-use OpenClaw alternative

English | 简体中文

Core Features

Server and Channel Collaboration Work in long-lived servers with channels, DMs, and reply threads. Mention persistent agents in the conversation, turn messages into trackable tasks, inspect execution progress in the drawer, and publish outputs into shared files for people and other agents to reuse.
Secure Sandbox All tasks run in an isolated container. Feel free to install dependencies, modify files, and execute commands — without affecting the host environment.
- Local Directory Mounting — mount host directories into the sandbox so the agent can work with your real project files directly (self-hosted only)
More Than a Chatbot
- Supports Plan Mode, conversation queueing, conversation termination ...
- Project management: organize work across tasks and contexts, and set project-level defaults for model, preset, Git repo, local mounts, and project files
- File uploads: accept and work with multiple file formats
Polished, Productive UI
- Artifacts view: render and preview many formats (HTML, PDF, Markdown, images, videos, Xmind, Excalidraw, Drawio, and more)
- Playback view: replay command I/O, browser sessions, and Skills/MCP tool calls
- Light/Dark mode support
Agentic Experience
- native Claude Code experience - Slash Commands, Plan Mode, AskQuestion ...
- Preset runtime config - reuse model, capability, tool, and sub-agent settings across projects and sessions
- MCP & Skills - easy to import and infinitely extensible
- Browser - Built-in browser for autonomous web research
- GitHub repo integration for code search and editing
- Background execution & scheduled triggers — your agent can keep running in the cloud even after you close the browser
Interaction
- Mobile support: control your agent anytime, anywhere
- IM integration: embedded backend messaging via DingTalk, Feishu, and Telegram, with push notifications and event subscriptions
- Self-hosting: one-click Docker deployment with a full runtime environment
- Cloud subscription: coming soon
- Multilingual support
Smart Memory Powered by mem0: the agent remembers your preferences, project context, and past interactions to deliver increasingly personalized help.
Many more powerful features waiting for you to discover!

Screenshots

Channel Collaboration	Shared Files

Start from a channel message, mention a persistent agent, and follow task progress in the execution drawer.	Published artifacts are grouped by agent so teammates and agents can reuse the same outputs.

Project Settings	Preset Editor

Set default configurations for your project — presets, local directory mounts, GitHub repos, knowledge base, and more.	DIY your cloud coworker — skills, MCP, sub-agents, and… system prompts & custom visual identity!

Quick Start

Chat in Project

Run the interactive setup script to automatically generate configuration and start services:

./scripts/quickstart.sh

Visit: http://localhost:3000 after startup completes.

For detailed deployment documentation and troubleshooting, please refer to the Deployment Guide.