Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

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 0.3.3rc1

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 0.3.3rc1
File Size Uploaded
osmosis_ai-0.3.3rc1.tar.gz 343.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for osmosis-ai 0.3.3rc1
File Interpreter ABI Platform
osmosis_ai-0.3.3rc1-py3-none-any.whl Python 3 none any Details

Total release size: 757.1 kB

Release files / osmosis_ai-0.3.3rc1.tar.gz

Download URL osmosis_ai-0.3.3rc1.tar.gz
Size 343.7 kB
Tags Source
SHA-256 checksum
How to use checksums
f9457d8bedad87832cc82535da7e1720c34c5bb603c0a5a42a89629ed2c529d4
BLAKE2b-256 checksum
How to use checksums
f8507b2d1c2ad52645870e7d49805bbee222f9021daa4320be4c7fbab5aeda69
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 8, 2026.

Transparency log

Release files / osmosis_ai-0.3.3rc1-py3-none-any.whl

Download URL osmosis_ai-0.3.3rc1-py3-none-any.whl
Size 413.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3d4defa514ff5a2de3b0d430a384d8560e293f86774294565f2090cebfe95bb3
BLAKE2b-256 checksum
How to use checksums
863502e083f9fbd04d52f43e584549dbee5bfe2bfe2749c41e4f70897734ebf8
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 8, 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