Biomni

This is an autonomous biomedical research agent from Stanford's SNAP lab that decomposes complex biology questions into executable analysis pipelines. Point it at CRISPR screening design, single-cell RNA-seq analysis, GWAS interpretation, or drug ADMET prediction and it generates and runs the code itself while pulling from 11GB of integrated databases. The framework is genuinely useful for multi-step biological reasoning tasks, though be aware it executes LLM-generated code with full system privileges, so you'll want proper sandboxing in production. Works with Claude, GPT-4, and other major LLM providers. Best suited for researchers who need to chain together genomics tools and biological knowledge retrieval without writing boilerplate analysis scripts.

skills.sh installs: 321
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill biomni --agent claude-code

Installs into .claude/skills of the current project.

Files

Biomni

Overview

Biomni is an open-source biomedical AI agent framework from Stanford's SNAP lab that autonomously executes complex research tasks across biomedical domains. Use this skill when working on multi-step biological reasoning tasks, analyzing biomedical data, or conducting research spanning genomics, drug discovery, molecular biology, and clinical analysis.

Core Capabilities

Biomni excels at:

Multi-step biological reasoning - Autonomous task decomposition and planning for complex biomedical queries
Code generation and execution - Dynamic analysis pipeline creation for data processing
Knowledge retrieval - Access to ~11GB of integrated biomedical databases and literature
Cross-domain problem solving - Unified interface for genomics, proteomics, drug discovery, and clinical tasks