{"name":"Biomni: A General-Purpose Biomedical AI Agent for Research","description":"Biomni is a general-purpose biomedical AI agent designed to autonomously execute a wide range of research tasks across diverse biomedical subfields. It integrates cutting-edge large language model reasoning with retrieval-augmented planning and code-based execution. This powerful tool helps scientists significantly enhance research productivity and generate testable hypotheses.","github":"https://github.com/snap-stanford/Biomni","url":"https://osrepos.com/repo/snap-stanford-biomni","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/snap-stanford-biomni","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/snap-stanford-biomni.md","json":"https://osrepos.com/repo/snap-stanford-biomni.json","topics":["agent","ai","biomedicine","python","llm","research","bioinformatics","stanford"],"keywords":["agent","ai","biomedicine","python","llm","research","bioinformatics","stanford"],"stars":null,"summary":"Biomni is a general-purpose biomedical AI agent designed to autonomously execute a wide range of research tasks across diverse biomedical subfields. It integrates cutting-edge large language model reasoning with retrieval-augmented planning and code-based execution. This powerful tool helps scientists significantly enhance research productivity and generate testable hypotheses.","content":"## Introduction\nBiomni is an innovative, general-purpose biomedical AI agent developed by SNAP Stanford. It is designed to autonomously execute a wide range of research tasks across diverse biomedical subfields, significantly enhancing research productivity. By integrating cutting-edge large language model (LLM) reasoning with retrieval-augmented planning and code-based execution, Biomni empowers scientists to generate testable hypotheses and streamline complex workflows.\n\n## Installation\nTo get started with Biomni, follow these steps for installation and environment setup.\nFirst, set up the environment by following the instructions in the `biomni_env/README.md` file within the repository.\nThen, activate the environment:\nbash\nconda activate biomni_e1\n\nInstall the Biomni pip package:\nbash\npip install biomni --upgrade\n\nFor the latest updates, install directly from the GitHub source:\nbash\npip install git+https://github.com/snap-stanford/Biomni.git@main\n\nFinally, configure your API keys for LLM providers like Anthropic or OpenAI. You can do this by creating a `.env` file or setting shell environment variables, as detailed in the official [Biomni repository](https://github.com/snap-stanford/Biomni){:target=\"_blank\"}.\n\n## Examples\nOnce installed and configured, Biomni can be used to execute biomedical tasks using natural language.\nHere are some basic usage examples:\npython\nfrom biomni.agent import A1\n\n# Initialize the agent with data path, Data lake will be automatically downloaded on first run (~11GB)\nagent = A1(path='./data', llm='claude-sonnet-4-20250514')\n\n# Execute biomedical tasks using natural language\nagent.go(\"Plan a CRISPR screen to identify genes that regulate T cell exhaustion, generate 32 genes that maximize the perturbation effect.\")\nagent.go(\"Perform scRNA-seq annotation at [PATH] and generate meaningful hypothesis\")\nagent.go(\"Predict ADMET properties for this compound: CC(C)CC1=CC=C(C=C1)C(C)C(=O)O\")\n\nBiomni also provides a Gradio-based web interface for interactive use. You can launch it with:\npython\nfrom biomni.agent import A1\n\nagent = A1(path='./data', llm='claude-sonnet-4-20250514')\nagent.launch_gradio_demo()\n\nRemember to install Gradio separately: `pip install \"gradio>=5.0,<6.0\"`.\n\n## Why Use Biomni?\nBiomni offers several compelling reasons for researchers and developers in the biomedical field:\n*   **General-Purpose AI Agent**: It can handle a wide array of research tasks across various biomedical subfields, from experimental planning to data analysis.\n*   **LLM-Powered Reasoning**: Leverages advanced large language models for intelligent planning, retrieval-augmented generation, and code-based execution.\n*   **Enhanced Productivity**: Automates complex, multi-step research workflows, allowing scientists to focus on higher-level problem-solving.\n*   **Know-How Library**: Integrates a curated collection of best practices, protocols, and troubleshooting guides, providing domain expertise on demand.\n*   **Biomni-R0 Model**: Features a specialized reasoning model, Biomni-R0, built on Qwen-32B, optimized for tool use and complex biological problem-solving.\n*   **Biomni-Eval1 Benchmark**: Provides a comprehensive evaluation benchmark for assessing biological reasoning capabilities across 10 diverse tasks.\n*   **Community-Driven Development**: Welcomes contributions for new tools, datasets, software integrations, benchmarks, and know-how documents, fostering an open-science ecosystem.\n\n## Links\nExplore Biomni further through these official resources:\n*   **GitHub Repository**: [https://github.com/snap-stanford/Biomni](https://github.com/snap-stanford/Biomni){:target=\"_blank\"}\n*   **Official Web UI**: [https://biomni.stanford.edu](https://biomni.stanford.edu){:target=\"_blank\"}\n*   **Research Paper**: [https://www.biorxiv.org/content/10.1101/2025.05.30.656746v1](https://www.biorxiv.org/content/10.1101/2025.05.30.656746v1){:target=\"_blank\"}\n*   **Join Slack**: [https://join.slack.com/t/biomnigroup/shared_invite/zt-3avks4913-dotMBt8D_apQnJ3mG~ak6Q](https://join.slack.com/t/biomnigroup/shared_invite/zt-3avks4913-dotMBt8D_apQnJ3mG~ak6Q){:target=\"_blank\"}\n*   **Follow on X**: [https://x.com/ProjectBiomni](https://x.com/ProjectBiomni){:target=\"_blank\"}\n*   **Follow on LinkedIn**: [https://www.linkedin.com/company/project-biomni](https://www.linkedin.com/company/project-biomni){:target=\"_blank\"}","metrics":{"detailViews":4,"githubClicks":4},"dates":{"published":null,"modified":"2026-01-15T12:01:15.000Z"}}