Skip to main content

Skill-first LLM agent platform with multi-channel bridging

Project description

MetaClaw

Skill-first LLM agent platform with multi-channel bridging. MetaClaw is a self-improving AI agent that connects to your favorite chat platforms (Slack, Discord, Telegram, WeChat, and more) and can read files, write code, run commands, and learn new skills autonomously.

Requirements

  • Python 3.10 or later
  • pip

Quick Start

# Install
pip install metaclaw-ai

# Interactive setup wizard
metaclaw init

# Start interactive agent
metaclaw run

# Or start server with channels
metaclaw start

Source Code

The full source code lives at https://github.com/yetone/metaclaw-src.

Reproducibility guarantee: the source repository contains every file needed to produce exactly this distributed artifact. You can clone it and run pip install -e . to obtain an identical package. The build process is recorded and publicly verifiable — see the asciinema session below.

Build Recording

A complete, unedited terminal recording of the build from source is available here:

asciicast

This recording demonstrates that the source code at https://github.com/yetone/metaclaw-src can and does build this exact artifact without modification.

License

See the source repository for license details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

metaclaw_ai-0.2.0.tar.gz (43.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

metaclaw_ai-0.2.0-py3-none-any.whl (60.9 kB view details)

Uploaded Python 3

File details

Details for the file metaclaw_ai-0.2.0.tar.gz.

File metadata

  • Download URL: metaclaw_ai-0.2.0.tar.gz
  • Upload date:
  • Size: 43.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.16

File hashes

Hashes for metaclaw_ai-0.2.0.tar.gz
Algorithm Hash digest
SHA256 d44f0c2383224863f46283cf37dfb45a804436c2fce8b59fce6887b1bf72bea4
MD5 4d5786bc3a37bc62087e88dfaee22b28
BLAKE2b-256 fbc615170f354c5309860b1d18609bea8927c88e9b86f829fe2650dd1f2a8a53

See more details on using hashes here.

File details

Details for the file metaclaw_ai-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: metaclaw_ai-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 60.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.16

File hashes

Hashes for metaclaw_ai-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 352f0a4be354ee41c10ef3395af0e92a6ef7aa6c844d63b13ddb5fb607b7d204
MD5 651d4f951211c6426e7d480edaecc7b0
BLAKE2b-256 ec09c668a6ee2dcdb980cfd088176c6637c71370d942223cf05c822e59842154

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page