TxAgent

github.com/mims-harvard/txagent
Idle634updated 11 months ago
Python
MIT

AI agent for therapeutic reasoning across a universe of tools, achieving 92.1% accuracy in drug reasoning and outperforming GPT-4o by 25.8% (Harvard MIMS, 2025)

Sourced from

  • GitHubgithub.com/mims-harvard/txagent
  • Awesome AI for Sciencegithub.com/mims-harvard/txagent

Related resources

Multimodal LLM-based AI agent enabling deep research in spatial transcriptomics, automating analysis and interpretation of spatial gene expression data (Harvard LiuLab, bioRxiv 2025)

Active581 month ago
Jupyter Notebook
Apache-2.0

DeepMind's Olympiad-level geometry theorem prover combining neural language model with symbolic deduction engine, AlphaGeometry2 solves 84% of IMO geometry problems (42/50) at gold-medalist level (Nature 2024)

Active4.9K5 months ago
Python
Apache-2.0

Official Jupyter extension with `%%ai` magic commands and sidebar chat assistant, connecting multiple model providers and local inference

Active4.3K1 month ago
Python
BSD-3-Clause

General-purpose biomedical AI agent integrating LLM reasoning with retrieval-augmented planning and code-based execution to autonomously execute diverse biomedical research tasks and generate testable hypotheses (Stanford SNAP, bioRxiv 2025)

Active3.2K1 month ago
Python
Apache-2.0

End-to-end autonomous AI research engine that turns an idea into a complete LaTeX paper by dispatching real computational experiments to local GPUs or SLURM clusters, collecting actual results, generating figures/tables, and writing a data-grounded manuscript rather than LLM hallucinations (OpenRaiser, 1.5K+ stars, MIT License, 2026)

Active1.5K1 month ago
Python
MIT

Democratizing AI scientists by transforming any LLM into research systems with 600+ scientific tools (Harvard MIMS)

Active1.4K1 month ago
Python
Apache-2.0