Repositories list

• BixBench

  Public
  Benchmark for LLM-based Agents in Computational Biology

  bioinformaticsartificial-intelligencelanguage-agents

  Python

  •

  Apache License 2.0

  •3•26•1•0•Updated Mar 26, 2025Mar 26, 2025

• ldp

  Public
  Agent framework for constructing language model agents and training on constructive tasks.

  reinforcement-learningartificial-intelligencelanguage-agents

  Python

  •

  Apache License 2.0

  •10•68•4•11•Updated Mar 21, 2025Mar 21, 2025

• paper-qa

  Public
  High accuracy RAG for answering questions from scientific documents with citations

  searchscienceai+ 1rag

  Python

  •

  Apache License 2.0

  •699•7.1k•111•1•Updated Mar 20, 2025Mar 20, 2025

• data-analysis-crow

  Public
  An aviary-based data science agent based on jupyter notebooks

  bioinformaticsjupyter-notebookdata-analysis+ 1language-agent

  HTML

  •

  Apache License 2.0

  •3•11•0•0•Updated Mar 17, 2025Mar 17, 2025

• trl

  Public
  FutureHouse fork of trl

  Python

  •

  Apache License 2.0

  •1.7k•0•0•5•Updated Mar 12, 2025Mar 12, 2025

• aviary

  Public
  Gymnasium framework for training language model agents on constructive tasks

  reinforcement-learningartificial-intelligencelanguage-agents

  Python

  •

  Apache License 2.0

  •18•154•6•2•Updated Mar 11, 2025Mar 11, 2025

• llm-client

  Public archive
  Central LLM client for use by Aviary and PaperQA

  Python

  •

  Apache License 2.0

  •0•2•0•0•Updated Feb 23, 2025Feb 23, 2025

• LAB-Bench

  Public
  Evaluation dataset for AI systems intended to benchmark capabilities foundational to scientific research in biology

  Python

  •

  Creative Commons Attribution Share Alike 4.0 International

  •2•41•2•0•Updated Feb 18, 2025Feb 18, 2025

• LitQA

  Public archive
  LitQA Eval: A difficult set of scientific questions that require context of full-text research papers to answer

  Python

  •

  Other

  •5•38•2•0•Updated Dec 18, 2024Dec 18, 2024

• WikiCrow

  Public
  MIT License

  •2•37•0•0•Updated Oct 24, 2024Oct 24, 2024

• SWE-bench

  Public
  Fork of upstream

  Python

  •

  MIT License

  •452•0•0•0•Updated Jul 24, 2024Jul 24, 2024

• drugcrow

  Public
  April 2024 Hackathon Crow Project

  Python

  •

  MIT License

  •0•3•0•1•Updated Apr 28, 2024Apr 28, 2024