Skip to content

@SakanaAI Sakana AI

Change the repository type filter

All

    Repositories list

    37 repositories

    • repo

      Public
      Python
      •0•0•0•0•Updated Dec 17, 2025Dec 17, 2025

    • IASC

      Public
      LLMs for Constructed Languages
      HTML
      •
      Creative Commons Attribution Share Alike 4.0 International
      •3•36•1•0•Updated Dec 16, 2025Dec 16, 2025

    • ShinkaEvolve

      Public
      ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution
      Python
      •
      Apache License 2.0
      •124•741•6•5•Updated Dec 14, 2025Dec 14, 2025

    • Kamon

      Public
      Data and code for understanding and generation of Kamon.
      Python
      •
      Creative Commons Attribution Share Alike 4.0 International
      •4•31•0•0•Updated Dec 14, 2025Dec 14, 2025

    • Sudoku-Bench

      Public
      An AI benchmark for creative, human-like problem solving using Sudoku variants
      JavaScript
      •
      MIT License
      •14•143•1•0•Updated Dec 13, 2025Dec 13, 2025

    • ALE-Bench

      Public
      The official repository of ALE-Bench
      Python
      •
      Apache License 2.0
      •16•139•2•0•Updated Dec 13, 2025Dec 13, 2025

    • treequest

      Public
      A Tree Search Library with Flexible API for LLM Inference-Time Scaling
      Python
      •
      Apache License 2.0
      •65•503•1•0•Updated Dec 9, 2025Dec 9, 2025

    • continuous-thought-machines

      Public
      Continuous Thought Machines, because thought takes time and reasoning is a process.
      Python
      •
      Apache License 2.0
      •248•1.6k•0•3•Updated Dec 9, 2025Dec 9, 2025

    • TinySwallow-ChatUI

      Public
      Browser-based chat UI for TinySwallow-1.5B that runs without API calls.
      CSS
      •
      Apache License 2.0
      •8•128•0•0•Updated Dec 1, 2025Dec 1, 2025

    • robust-kbench

      Public
      Python
      •
      Apache License 2.0
      •9•71•3•0•Updated Nov 22, 2025Nov 22, 2025

    • neuroevolution-for-ai

      Public
      Neuroevolution Community
      2•6•0•0•Updated Nov 17, 2025Nov 17, 2025

    • mle-bench-shinka-agent

      Public
      MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
      Python
      •
      Other
      •189•0•0•0•Updated Nov 12, 2025Nov 12, 2025

    • petri-dish-nca

      Public
      Python
      •5•51•0•1•Updated Nov 6, 2025Nov 6, 2025

    • google-code-golf-2025

      Public
      Python
      •
      Apache License 2.0
      •0•4•0•0•Updated Oct 31, 2025Oct 31, 2025

    • AI-Scientist-v2

      Public
      The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
      Python
      •
      Apache License 2.0
      •362•1.9k•38•6•Updated Oct 24, 2025Oct 24, 2025

    • asal

      Public
      Automating the Search for Artificial Life with Foundation Models!
      Jupyter Notebook
      •
      Apache License 2.0
      •52•447•1•0•Updated Oct 23, 2025Oct 23, 2025

    • shachi

      Public
      Reimagining Agent-based Modeling with Large Language Model Agents via Shachi
      Python
      •
      Apache License 2.0
      •0•11•0•0•Updated Oct 10, 2025Oct 10, 2025

    • TAID

      Public
      Official implementation of "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models"
      Python
      •
      Apache License 2.0
      •9•119•3•0•Updated Oct 6, 2025Oct 6, 2025

    • natural_niches

      Public
      The code repository of the paper: Competition and Attraction Improve Model Fusion
      Jupyter Notebook
      •
      Apache License 2.0
      •33•168•1•0•Updated Aug 25, 2025Aug 25, 2025

    • BALROG

      Public
      Benchmarking Agentic LLM and VLM Reasoning On Games
      Python
      •
      MIT License
      •41•1•0•0•Updated Aug 19, 2025Aug 19, 2025

    • EDINET-Bench

      Public
      Evaluating the performance of LLMs on Japanese challenging financial tasks.
      Python
      •
      Apache License 2.0
      •3•27•0•0•Updated Jul 28, 2025Jul 28, 2025

    • TransEvalnia

      Public
      Reasoning-based Evaluation and Ranking of Translations.
      Python
      •
      Apache License 2.0
      •4•18•1•0•Updated Jul 18, 2025Jul 18, 2025

    • ab-mcts-arc2

      Public
      Python
      •
      Apache License 2.0
      •18•105•1•0•Updated Jun 30, 2025Jun 30, 2025

    • RLT

      Public
      Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.
      Python
      •
      Apache License 2.0
      •53•354•3•0•Updated Jun 23, 2025Jun 23, 2025

    • edinet2dataset

      Public
      edinet2dataset is a tool to construct financial dataset using EDINET.
      Python
      •
      Apache License 2.0
      •7•26•0•0•Updated Jun 11, 2025Jun 11, 2025

    • text-to-lora

      Public
      Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input
      machine-learninglorafine-tuninghypernetworksllm
      Python
      •
      Apache License 2.0
      •64•927•2•0•Updated Jun 8, 2025Jun 8, 2025

    • L2D

      Public
      Large language models to diffusion finetuning code
      Python
      •
      Apache License 2.0
      •3•21•0•0•Updated Jun 2, 2025Jun 2, 2025

    • AI-Scientist

      Public
      The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬
      Jupyter Notebook
      •
      Apache License 2.0
      •1.7k•12k•89•21•Updated Apr 26, 2025Apr 26, 2025

    • AI-Scientist-ICLR2025-Workshop-Experiment

      Public
      Python
      •20•276•0•0•Updated Apr 18, 2025Apr 18, 2025

    • CycleQD

      Public
      CycleQD is a framework for parameter space model merging.
      Python
      •
      Apache License 2.0
      •6•45•0•0•Updated Feb 1, 2025Feb 1, 2025