
Biomni is a general-purpose biomedical AI agent from Stanford that carries out research tasks across biomedical fields. It combines LLM reasoning, retrieval-augmented planning and code execution.
AgentFree
Step 1: Run the setup script and activate the biomni_e1 conda environment.
Step 2: Install the package with pip install biomni.
Step 3: Add your API keys in a .env file.
Step 4: Create an A1 agent with a data path.
Step 5: Call agent.go with a task in plain language, or launch the Gradio demo.
The README lists Anthropic, OpenAI, Azure OpenAI, Gemini, Groq, Bedrock, Ollama and custom endpoints.
The data lake is about 11GB and is fetched when you first create an agent. You can skip it if you only need tools that do not use it.
Yes. Call launch_gradio_demo to open a web UI, which needs Gradio 5.x.
Some are left out because of dependency conflicts. The README points to a known conflicts document with install notes.
Cell2SentenceCell2Sentence applies large language models to single-cell RNA data by turning each cell into a text sentence of gene names. The repository holds the code and tutorials for working with these models.
Biomni-E1Biomni is an open-source biomedical AI agent from Stanford's SNAP group that carries out research tasks from natural-language instructions. It combines language-model reasoning, retrieval-based planning and code execution.