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 with Daytona support
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. 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.