Skip to main content

The Unified System Layer for Agentic Intelligence

Project description

Charm Banner

Homepage · Documentation · Contributing · Discord

Charm: The Unified Platform for Agentic Intelligence

Current Status: v0.2.0 (Developer Preview)

We are building the Universal Interface Protocol. v0.2.0 focuses on the Development Layer, providing the Unified Agent Contract (UAC) and Wrapper SDK to turn existing agents into Universal Charm Agents.

Charm is a Unified System Layer that governs the development, execution, and distribution of AI agents.

It provides a standardized architecture that enables agents to assemble, interoperate, and scale across heterogeneous ecosystems, turning them into real, commercial-ready applications.


Why Charm?

Before you dive deeper, we’d like you to take a moment to read this blog post to understand our insights and perspective.

Getting started

To explore Charm’s core concepts and code in more detail, check out our documentation.

Installation

Charm is not published to PyPI yet.
To try the current demo from source:

  1. Clone the repository
    git clone https://github.com/CharmAIOS/Charm.git
    cd Charm
    
  2. Create and activate a virtual environment
    python3 -m venv .venv
    source .venv/bin/activate
    
  3. Install Charm in editable mode
    pip install -e .
    
  4. Run the working demo
    python src/charm/demo/demo_mock.py  # python -m charm.demo.demo_mock
    

Contributing

To learn how to contribute to Charm, please read the contribution guide here.

Contact

Changelog

Check our updates

License

Charm is licensed under the GNU Affero General Public License v3.0

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

charmos-0.3.0a1.tar.gz (28.3 kB view details)

Uploaded Source

Built Distribution

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

charmos-0.3.0a1-py3-none-any.whl (29.5 kB view details)

Uploaded Python 3

File details

Details for the file charmos-0.3.0a1.tar.gz.

File metadata

  • Download URL: charmos-0.3.0a1.tar.gz
  • Upload date:
  • Size: 28.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.11

File hashes

Hashes for charmos-0.3.0a1.tar.gz
Algorithm Hash digest
SHA256 ff870ce9a312776d588ecc6d07a8ad03b4f6303b5ca24bf901702abc11e55cea
MD5 91f21765d401fee2b89306258bf985f9
BLAKE2b-256 c1ad99b520eb7f828441c1f8eb3028769f11758c5d00d0b1bf1af0511b968f31

See more details on using hashes here.

File details

Details for the file charmos-0.3.0a1-py3-none-any.whl.

File metadata

  • Download URL: charmos-0.3.0a1-py3-none-any.whl
  • Upload date:
  • Size: 29.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.11

File hashes

Hashes for charmos-0.3.0a1-py3-none-any.whl
Algorithm Hash digest
SHA256 b7d22856ca4ee9fceef5f790aac01db607581d42e3f812c1a684beb5ada21299
MD5 06c845835cb37dd991d8a457dfa33c2f
BLAKE2b-256 b1b6065a133702ddb3db6667f69151b4909878071bfc350ba9cc38cd5e9b93a1

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