Skip to content

@TheDuckAI DuckAI

Change the repository type filter

All

    Repositories list

    17 repositories

    • DuckTrack

      Public
      Multimodal computer agent data collection program
      Python
      •
      MIT License
      •25•154•9•0•Updated Dec 5, 2025Dec 5, 2025

    • mini-swe-agent

      Public
      The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores 68% on SWE-bench verified!
      Python
      •
      MIT License
      •306•0•0•0•Updated Aug 21, 2025Aug 21, 2025

    • SWE-agent

      Public
      SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
      Python
      •
      MIT License
      •1.9k•0•0•0•Updated Aug 18, 2025Aug 18, 2025

    • preparedness

      Public
      Releases from OpenAI Preparedness
      Python
      •
      MIT License
      •114•0•0•0•Updated Aug 15, 2025Aug 15, 2025

    • mle-bench

      Public
      MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
      Python
      •
      Other
      •196•0•0•0•Updated Aug 14, 2025Aug 14, 2025

    • deepthink

      Public
      Python
      •0•0•0•0•Updated Jul 27, 2025Jul 27, 2025

    • SWE-bench-Live

      Public
      🚀 SWE-bench Goes Live!
      Python
      •
      MIT License
      •24•0•0•0•Updated Jul 25, 2025Jul 25, 2025

    • openevolve

      Public
      Open-source implementation of AlphaEvolve
      Python
      •
      Apache License 2.0
      •774•7•0•2•Updated Jul 10, 2025Jul 10, 2025

    • prm_annotation_platform

      Public
      JavaScript
      •1•4•10•0•Updated Feb 19, 2025Feb 19, 2025

    • prm

      Public
      Python
      •3•12•24•3•Updated Jan 17, 2025Jan 17, 2025

    • site

      Public
      JavaScript
      •
      MIT License
      •0•0•0•0•Updated Nov 22, 2023Nov 22, 2023

    • arb

      Public
      Advanced Reasoning Benchmark Dataset for LLMs
      benchmarkdatasetllm
      TypeScript
      •
      MIT License
      •3•47•6•1•Updated Nov 19, 2023Nov 19, 2023

    • chonk

      Public
      Python
      •
      MIT License
      •15•2•0•0•Updated Oct 18, 2023Oct 18, 2023

    • videorl

      Public
      Python
      •
      MIT License
      •1•5•13•4•Updated Oct 6, 2023Oct 6, 2023

    • scratchpad

      Public
      0•0•0•0•Updated Aug 25, 2023Aug 25, 2023

    • community-website

      Public
      Community website
      JavaScript
      •
      MIT License
      •1•0•1•0•Updated Aug 14, 2023Aug 14, 2023

    • donut

      Public
      Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
      Python
      •
      MIT License
      •548•2•0•0•Updated Nov 22, 2022Nov 22, 2022