snap-stanford/biomni

Biomni: a general-purpose biomedical AI agent

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 54 minutes ago
Added to GitGenius on September 17th, 2026
Created on March 19th, 2025
Open Issues & Pull Requests: 113 (+0)
GitHub issues: Enabled
Number of forks: 715
Total Stargazers: 3,897 (+0)
Total Subscribers: 38 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 8.0 hours
Mean response time: 5.3 days
90th percentile: 12.4 days
Tracked items: 124

Most active contributors

Sign in to see contributor activity.

How this project is maintained

95% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Three people close 88% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 58
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 281 days
Stale 30+ days: 51
Stale 90+ days: 43

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • enhancement (11)
  • bug (10)
  • new-dataset (5)
  • help wanted (4)
  • good first issue (3)
  • new-tool (2)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Biomni is a general-purpose biomedical AI agent that automates complex tasks in biomedical research and clinical domains.

The tool addresses the challenge of executing multi-step biomedical workflows that require reasoning across diverse data sources and specialized knowledge. Biomni operates as an agent system capable of understanding biomedical queries and orchestrating appropriate actions to retrieve, analyze, and synthesize information from various biomedical resources and datasets. Rather than requiring manual step-by-step execution, the agent can decompose complex biomedical problems into constituent tasks and execute them in sequence.

Biomni suits researchers and clinicians who need to automate repetitive biomedical analysis tasks or who work with complex queries spanning multiple data sources. It is particularly valuable for those conducting literature reviews, analyzing clinical data, or performing biomedical research that would benefit from automated reasoning and information synthesis. The project targets users who want to leverage AI capabilities without building custom automation pipelines for each specific biomedical task.

The project shows active development with regular code commits and ongoing refinement of the agent's capabilities. The codebase demonstrates attention to implementation quality through structured code organization and iterative improvements to the core agent system. Development activity reflects a focus on expanding the agent's ability to handle diverse biomedical tasks and improving its reasoning across different types of biomedical data and resources.