Skip to main content

The Unified System Layer for Agentic Intelligence

Project description

Charm Banner

Build PyPI Discord License X

Charm: The Unified Platform for Agentic Intelligence

Charm is a Unified Application Layer that enables agents to distribute, run, and scale across heterogeneous ecosystems, turning them into real, commercial-ready applications.

Getting Started

For a step-by-step walk through of Charm concepts and code, check out overview in our documentation.

Installation

Charm is available on PyPI. We recommend using uv for the best experience.

Standard Setup (For Agent Development)

If you only want to build and define agents

uv add charmos
# or
pip install charmos

Advanced Setup (For Local Cloud Runner)

If you want to simulate the isolated cloud environment locally

uv add charmos[runner]
# or
pip install charmos[runner]

Note: To use the docker simulation mode, you must have Docker Desktop or Docker Engine running on your machine.

Build and publish your first agent

Use the quickstart docs to install the CLI, build a starter agent, validate charm.yaml, and publish to Charm Store:

Documentation

Contributing

To know how to contribute to Charm, please read our contribution guide.

Security

Please report vulnerabilities privately using the process in SECURITY.md.

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-0.5.0.tar.gz (89.4 kB view details)

Uploaded Source

Built Distribution

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

charmos-0.5.0-py3-none-any.whl (108.7 kB view details)

Uploaded Python 3

File details

Details for the file charmos-0.5.0.tar.gz.

File metadata

  • Download URL: charmos-0.5.0.tar.gz
  • Upload date:
  • Size: 89.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for charmos-0.5.0.tar.gz
Algorithm Hash digest
SHA256 64dbd5a8b518f0fe4466e0e42926baf4351b9fa37722ce1032fd1db8b53ea072
MD5 ec98e146cda9274833ed69218d8ec700
BLAKE2b-256 664eebbac8f6b62b41cc9f359be3879fd113b4bee158f6114e732612c7f8e1c6

See more details on using hashes here.

Provenance

The following attestation bundles were made for charmos-0.5.0.tar.gz:

Publisher: publish-pypi.yml on CharmAIOS/Charm

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file charmos-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: charmos-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 108.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for charmos-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b45719b795014f21e0e431a6aa5cf49e8b0fddbbed00951a9d5f8e7c5889e027
MD5 f8ebbebfba8eda7a657b162a1fa252f2
BLAKE2b-256 254ef7b8c2b9bbc92f42e7da3046904c89e07fbdf38c1341a17154815b1da349

See more details on using hashes here.

Provenance

The following attestation bundles were made for charmos-0.5.0-py3-none-any.whl:

Publisher: publish-pypi.yml on CharmAIOS/Charm

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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