A community-driven registry for Claude, Cursor, Windsurf, Cline & more. Not affiliated with Anthropic.
Are you the author? Sign in to claim
Ultra-Lightweight, Pure Python Multimodal Agent.
The Ultra-Lightweight, Pure Python Kernel for Multimodal AI Agents.
pip install mmclaw
Home: https://mmclaw.github.io
GitHub: https://github.com/CrawlScript/MMClaw
English | 中文说明
Note: This project was previously named pipclaw (pre-v0.0.11).
MMClaw is a minimalist, 100% Pure Python autonomous agent kernel. While frameworks like OpenClaw offer great power, they often introduce heavy dependencies like Node.js, Docker, or complex C-extensions.
MMClaw strips away the complexity, offering a crystal-clear, readable architecture that serves as both a production-ready kernel and a comprehensive tutorial on building modern AI agents.
WeChat (微信) connector — Pure Python, zero extra dependencies.
Bind your agent to WeChat in one second: run mmclaw config, select WeChat mode, and scan the QR code. That's it. No Node.js, no webhooks, no app registration. Your agent is live on WeChat instantly.
ClawMeets is an agent-to-agent (A2A) messaging platform developed by the same team behind MMClaw — and natively supported by MMClaw out of the box. Each account is identified by a 12-character public address (safe to share) and authenticated by a private token. No username or password — sign up at any time with a single command.
Control your AI agent from anywhere, through the apps you already use.
mmclaw config.No compiling, no heavy setup. Just pip and run.
pip install mmclaw
mmclaw run
If you plan to use Feishu (飞书) as your connector, install with the [all] option to include the required lark-oapi dependency:
pip install "mmclaw[all]"
The trend in AI agents is moving towards massive complexity. MMClaw moves towards clarity. Most developers don't need a 400,000-line black box. They need a reliable, auditable kernel that handles the agent loop and tool-calling while remaining light enough to be modified in minutes. MMClaw is the "distilled essence" of an autonomous bot.
MMClaw allows you to interact with your agent through multiple channels:
# To change your mode or LLM settings
mmclaw config
MMClaw supports a wide range of LLM providers:
api.minimax.io) and China (api.minimaxi.com) endpoints.MMClaw supports slash commands such as:
/new — Start a fresh session, clearing the current conversation history./stop — Immediately cancel the current job, terminating any running tool or shell command.Skills extend MMClaw with new capabilities.
mmclaw skill list
mmclaw skill install [--force] <path-or-url> # local dir or URL (e.g. from ClawHub)
mmclaw skill uninstall <skill-name>
You can also just ask your agent to install a skill via chat (Telegram, WhatsApp, etc.) — it will guide you through finding and installing from ClawHub.
By default, MMClaw stores all data (config, skills, memory, sessions) in ~/.mmclaw. Most users never need to change this.
To run multiple independent agents — each with its own config, skills, and memory — pass -w / --workspace:
mmclaw run -w ~/.mmclaw_work
mmclaw run -w ~/.mmclaw_personal
mmclaw config -w ~/.mmclaw_work # configure a specific workspace
The workspace directory is created automatically on first run. We recommend naming it ~/.mmclaw_<label> (e.g. ~/.mmclaw_work, ~/.mmclaw_personal). Each instance is a fully isolated process — Ctrl-C one without affecting the others.
Common use cases: multiple Telegram bots (e.g. one for personal use, one for coding, one for paper writing), or mixing connectors across apps — each workspace fully isolated with its own config, skills, and memory.
Just tell your agent what to do and when — it handles the rest:
"Remind me to drink water every 30 minutes" "Send me a weather summary every day at 8am"
You can also list, delete, or modify scheduled tasks anytime by just asking.
Sign up for a ClawMeets account via Agent Chat and get a share card like this — copy and send it to anyone:
---- Agent ID (ClawMeets) ----
a3f9bc112d44
------------------------------
(Paste this to your agent to add me as a contact)
When a friend pastes their card to MMClaw, just give them a nickname (local only — the server never sees it). Messages are exchanged securely via public address. Send/receive messages with file attachments, manage contacts by nickname, check your inbox, and get notified of new messages automatically — all from within MMClaw.
-p)Run a single prompt non-interactively — the agent executes the full agentic loop (tool calls, multi-step tasks) and exits when done. No session history or global memory — clean context every run. LLM provider settings and skills are still loaded from your workspace (default ~/.mmclaw, or specify via -w).
mmclaw run -p "check disk usage and summarize"
mmclaw run -p "check disk usage and summarize" -w ~/.mmclaw_work
# add --global-memory to let the agent read/write global memory shared with your interactive sessions
mmclaw run -p "summarize my tasks and save key points to memory" --global-memory
Developed with ❤️ for the Python community. Let's keep it simple.
干净、强大、属于你的 AI Agent 平台 --AI agents, without the clutter.
An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance
npx CLI installing 100+ agents, commands, hooks, and integrations in one command
Pocket Flow: Codebase to Tutorial