Skip to main content

The Unified Application 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-0.5.1.tar.gz (89.5 kB view details)

Uploaded Source

Built Distribution

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

charmos-0.5.1-py3-none-any.whl (108.7 kB view details)

Uploaded Python 3

File details

Details for the file charmos-0.5.1.tar.gz.

File metadata

  • Download URL: charmos-0.5.1.tar.gz
  • Upload date:
  • Size: 89.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for charmos-0.5.1.tar.gz
Algorithm Hash digest
SHA256 1dd78796b8e1559ed4380b086d9135a2dc98dcf25353b0baf362078fb8b12c00
MD5 dd6a9cd8fef6f068da3819dcfa28ceb8
BLAKE2b-256 3c6d2084ada11cc5f909e0a0e21f47e8d9f5e3ec854dd4e0288cc0316e93ce63

See more details on using hashes here.

Provenance

The following attestation bundles were made for charmos-0.5.1.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-0.5.1-py3-none-any.whl.

File metadata

  • Download URL: charmos-0.5.1-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-0.5.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ca34daa1756aca63215508af96f043ec62d53a690f293a3bc7607ce403a812b8
MD5 714a99ae694340b42deeae9d362abca5
BLAKE2b-256 f960a248997f28edebfe432b05aba7f766d269ecbd3ed70dd489e358b220c75a

See more details on using hashes here.

Provenance

The following attestation bundles were made for charmos-0.5.1-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