Curie vs Biomni
AI agents for scientific research compared
Curie and Biomni are Python projects that use AI agents to help carry out research tasks. Curie focuses on automating scientific experiments from hypothesis to report, while Biomni coordinates biomedical tasks using retrieval, model reasoning, and code execution.
Curie: Automate Scientific Experiments with AI Agents
Curie is a Python framework that uses AI agents to plan, run, analyze, and report on scientific experiments. It suits researchers who want to automate exploratory or machine-learning work, but its inactive development and lack of recent releases warrant caution.
Biomni: Run Biomedical Research Tasks with an AI Agent
Biomni is a Python biomedical AI agent that combines large language model reasoning, retrieval-augmented planning, and code execution to help researchers carry out tasks across biomedical fields. It also offers a web interface and supports external tools through MCP.
| Curie | Biomni | |
|---|---|---|
| Language | Python | Python |
| License | Apache-2.0 | Apache-2.0 |
| Stars | 370 | 4k |
| Forks | 32 | 728 |
| Last analyzed | Oct 9, 2026 | Oct 22, 2026 |
Key differences
- Curie is designed for scientific experiments across areas including machine learning and system analysis; Biomni focuses on biomedical research workflows.
- Curie emphasizes experiment execution, verification, and reports; Biomni emphasizes biomedical retrieval, a curated know-how library, and integrations with external tools.
- Curie accepts a user’s dataset and optional starter code; Biomni can draw on its biomedical data lake, which downloads about 11 GB on first use by default.
- Curie has 370 stars and 32 forks and has had no commits or releases in over a year; Biomni has 3.9k stars and 723 forks, and its described release was frozen as of April 15, 2025.
- Both use Python and Apache-2.0. Biomni also warns that its agent can run generated code with full system privileges, so it recommends an isolated, sandboxed environment.
Choose Curie if you…
- want an agent to run scientific experiments on your dataset or starter code and produce reviewable reports.
- need a workflow that includes experiment verification or an AutoML search.
- are prepared to check the prerelease’s behavior and compatibility and account for the listed setup requirements.
Choose Biomni if you…
- need an agent focused on biomedical research tasks and tool-assisted workflows.
- want to connect natural-language requests with biomedical resources, external tools, or MCP integrations.
- can accommodate the data download and isolate execution of LLM-generated code in a sandboxed environment.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.