Skip to main content

Osmosis

Platform PyPI Python Codecov License Docs

osmosis-ai

⚠️ Warning: osmosis-ai is still in active development. APIs may change between versions.

Python SDK and CLI for Osmosis AI, a platform for training LLMs with reinforcement learning. Implement an AgentWorkflow and a concrete Grader in Python, then use the CLI to submit evaluation and training runs from an Osmosis workspace directory.

Installation

Requires Python 3.12+.

pip install osmosis-ai                     # CLI + framework-neutral rollout core
pip install "osmosis-ai[server]"            # + generic FastAPI rollout server
pip install "osmosis-ai[eval]"              # + local evaluation runner and dataset support
pip install "osmosis-ai[strands]"           # + Strands integration
pip install "osmosis-ai[openai-agents]"     # + OpenAI Agents integration
pip install "osmosis-ai[harbor]"            # + Harbor backend (uses an externally provided SkyPilot runtime)
pip install "osmosis-ai[rubric]"            # + LLM-as-judge rubric evaluation
pip install "osmosis-ai[parquet]"           # + Parquet dataset support
pip install "osmosis-ai[full]"              # every optional feature
# or with uv:  uv add osmosis-ai

There is one distribution, osmosis-ai. The harbor extra installs Harbor with its Daytona environment dependencies. It does not install Harbor's skypilot extra because the rollout runtime provides SkyPilot. See Installation for product setup and CONTRIBUTING.md for development setup.

Documentation

Guides, quickstart, and the full CLI reference live at docs.osmosis.ai.

  • Quickstart — run the multiply example end to end, from onboarding to evaluation run to training run
  • CLI command reference — every osmosis command and flag, plus the --json / --plain output contract for AI agents and CI/CD
  • Workspace setup — repository layout, config files, and Git Sync
  • Rollouts — AgentWorkflow, Grader, integrations, and execution backends
  • Releases — version history and breaking changes between releases

Building on or contributing to the SDK itself? See the code-anchored developer docs in docs/ (start with docs/architecture.md) alongside CONTRIBUTING.md.

Contributing

See CONTRIBUTING.md for development setup, testing, linting, and PR guidelines.

License

MIT License - see LICENSE file for details.

Release files for osmosis-ai 0.3.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for osmosis-ai 0.3.2
File Size Uploaded
osmosis_ai-0.3.2.tar.gz 351.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for osmosis-ai 0.3.2
File Interpreter ABI Platform
osmosis_ai-0.3.2-py3-none-any.whl Python 3 none any Details

Total release size: 773.4 kB

Release files / osmosis_ai-0.3.2.tar.gz

Download URL osmosis_ai-0.3.2.tar.gz
Size 351.0 kB
Tags Source
SHA-256 checksum
How to use checksums
e8c316ae29507decb2a162614873e15bb2fa42f7611ad72528b91945394cb89a
BLAKE2b-256 checksum
How to use checksums
4cc14e8883bebcc75841078e44ab6f8a0cbe61fc62fc80c58b1fdb001e136839
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 1, 2026.

Transparency log

Release files / osmosis_ai-0.3.2-py3-none-any.whl

Download URL osmosis_ai-0.3.2-py3-none-any.whl
Size 422.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
58136143eaf0f1d41916d30484ff915e48f2c31b26a8f8aa2fbb698ac2bc0dee
BLAKE2b-256 checksum
How to use checksums
4f287bb9b674f53b9804b39d622a7154b2ee143af4442666ba6e98811e08f0b5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 1, 2026.

Transparency log
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page