# snap-stanford/Biomni

Biomni: a general-purpose biomedical AI agent

Repository: https://github.com/snap-stanford/Biomni
Canonical: https://ross.abutalabs.com/products/biomni
Homepage: https://biomni.stanford.edu
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, ai, biomedicine
Last push: 2026-08-24T18:55:59+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 54, longevity 38
- inputs: {"age_days": 532, "days_push": 9, "days_rel": 310, "gap_med": 28, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3790, forks 696 (observed 2026-08-28T04:08:18.699518+00:00)

## What it is
Biomni is a general-purpose biomedical AI agent from Stanford that autonomously executes research tasks across biomedical subfields. It combines LLM reasoning with retrieval-augmented planning and code-based execution to boost research productivity and generate testable hypotheses.

## Use cases
- run autonomous biomedical research tasks
- generate testable scientific hypotheses with an LLM agent
- analyze genomics or bioinformatics data with AI
- plan and execute multi-step biology experiments computationally
- query biomedical databases with a natural language agent

## When to choose
- you need an AI agent specialized for biomedical research workflows
- you want retrieval-augmented planning plus code execution for life-science tasks
- you are a computational biologist wanting to automate analysis pipelines

## When to avoid
- you need a general-purpose agent with no biomedical focus
- you cannot provide LLM API keys or manage a heavy conda environment
- you need a production clinical or diagnostic tool rather than a research assistant

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, rag, llm-inference, machine-learning
- domain: artificial-intelligence, bioinformatics, healthcare, large-language-models
- platform: python, cli, cross-platform
- tags: biomedical-ai, research-agent, hypothesis-generation, llm-agent, scientific-research, ai-agents

## Member repositories
- snap-stanford/Biomni (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:18.699518+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:27:27.346587+00:00, confidence not recorded.
  - readme: https://github.com/snap-stanford/Biomni (fetched 2026-08-28T04:08:18.699518+00:00, sha b515a5cde95f)
  - homepage: https://biomni.stanford.edu (fetched 2026-08-29T09:22:10.997713+00:00, sha cdd53c4c5246)
  - registry_pypi: https://pypi.org/pypi/biomni/json (fetched 2026-08-29T09:22:11.001948+00:00, sha 31e42b6f6b52)
- Data as of 2026-08-30T08:39:29.467469+00:00.