Biomni
General-purpose biomedical AI agent that autonomously runs research tasks by combining LLM reasoning with code execution.
Agent by Stanford SNAP
IndexedApache-2.0★ 4,005
Get started
Setup steps are in the repository. Website · Repository
About
Biomni is a general-purpose biomedical AI agent designed to execute a wide range of research tasks across biomedical subfields autonomously. It combines LLM reasoning and retrieval-augmented planning with code-based execution. The README covers installation with pip and a Python A1 agent, and lists API key setups for providers including Anthropic, OpenAI, Gemini, Groq, Azure OpenAI, AWS Bedrock, Ollama and custom endpoints.
Use cases: research, deep-research, data-analysis
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Jobs
- researchREADME
- Autonomy
- Autonomous: runs tasks end to end and reports backREADME
- Where you use it
- Web, APIREADME
- Hosting
- Hosted or self-hostedREADME
- Models
- anthropic, openai, azure-openai, google, groq, aws-bedrock, ollamaREADME
- Interfaces
- sdkREADME
- Open source
- Yes
Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.
Built on
Frameworks named in its dependency files.
Signals
- Stars
- 4,005
- Forks
- 730
- Open issues
- 66
- Last commit
- Jan 15, 2026 (9 months ago)
- Last release
- Oct 27, 2025 (0 years ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/snap-stanford/Biomni
- Website
- biomni.stanford.edu
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
Biomni. Agent Mart. https://agentmart.dev/agents/biomni (last updated 2026-10-24)