reproducibility repositories

Trending repositories tagged reproducibility, ranked by trending score. Updated daily.

  1. 1
    LearnPrompt/awesome-seedance

    ๐ŸŽฌ Evidence-led Seedance 2.5 / 2.0 prompt library: 1000+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 80+ installable AI-video Skills. Synced daily from goodcase.ai. EN / ไธญๆ–‡ / ๆ—ฅๆœฌ่ชž.

    GitHub ยท JavaScript ยท 2,606 stars ยท 392 forks ยท +35 stars in 24 hours ยท Trending score 2.84

  2. 2
    wandb/wandb

    The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

    GitHub ยท Python ยท 11,332 stars ยท 922 forks ยท +8 stars in 24 hours ยท Trending score 1.96

  3. 3
    chutingyean/Agent-Cockpit

    Evidence-chain whiteboard + MCP server for AI research agents: every claim traces back to the run and code that produced it. ่ฎ“ AI agent ๅš็ ”็ฉถๆ™‚๏ผŒๆฏๅ€‹็ต่ซ–้ƒฝ่ƒฝ่ฟฝๅˆฐ็”ข็”Ÿๅฎƒ็š„็จ‹ๅผ็ขผใ€‚Claude Code ยท Codex ยท Cursor ยท Gemini CLI

    GitHub ยท JavaScript ยท 514 stars ยท 13 forks ยท +5 stars in 24 hours ยท Trending score 1.69

  4. 4
    ailev/FPF

    FPF (First Principles Framework) Library: methods and pattern languages for open-ended development and a shared culture of thinking and acting among people and AI agents. Use individual methods or combine them to solve difficult problems and expand capabilities.

    GitHub ยท 547 stars ยท 98 forks ยท +3 stars in 24 hours ยท Trending score 1.32

  5. 5
    sipyourdrink-ltd/bernstein

    Open-source AI agent governance. Write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

    GitHub ยท Python ยท 1,216 stars ยท 185 forks ยท +3 stars in 24 hours ยท Trending score 1.27

  6. 6
    yzlin286-wq/Deepscient

    ่ฎฉ AI ไธŽไบบ็ฑปไธ€่ตทๆ”ปๅ…‹็œŸๆญฃ็š„็ง‘ๅญฆ้šพ้ข˜ โ€”โ€” 12 ้˜ถๆฎต 55 ้—จ ยท 36 ๅทฅๅ…ท ยท 98 ๆกๆŠ€่ƒฝ ยท ่ฏๆฎ้“พไธŽๅฏๅค็Žฐ

    GitHub ยท JavaScript ยท 986 stars ยท 22 forks ยท +2 stars in 24 hours ยท Trending score 1.25

  7. 7
    dolev31/lasagna

    Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

    GitHub ยท Python ยท 37 stars ยท 14 forks ยท +2 stars in 24 hours ยท Trending score 0.91

  8. 8
    AOSSIE-Org/OpenVerifiableLLM

    Local Fully Open, Open-Weight, Open-Data, Verifiable LLMs. Language models you can check yourself: every training step recomputable bit for bit.

    GitHub ยท Python ยท 26 stars ยท 64 forks ยท 0 stars in 24 hours ยท Trending score 0.82

  9. 9
    ChiShengChen/neural-signals-101

    Beginner tutorial: ML & signal processing on neural signals (EEG) in Python โ€” raw recordings to honest evaluation, in runnable notebooks. MIT.

    GitHub ยท Jupyter Notebook ยท 20 stars ยท 2 forks ยท 0 stars in 24 hours ยท Trending score 0.59

  10. 10
    ThinkFlowLab/nullius

    An evaluation framework for AI agents. Bring any benchmark, agent or capability, run it on your machines, and inspect the evidence behind every score.

    GitHub ยท Python ยท 8 stars ยท 4 forks ยท 0 stars in 24 hours ยท Trending score 0.57

  11. 11
    Deathburgerz013/HOLO-Invariant

    Deterministic continuity and verification framework for preserving corrections, uncertainty, evidence, and reconstruction across AI and software handoffs.

    GitHub ยท Python ยท 18 stars ยท 2 forks ยท +1 stars in 24 hours ยท Trending score 0.55

  12. 12
    inflexa-ai/inflexa

    Local-first CLI for reproducible biological analysis, with provenance tracked on every step.

    GitHub ยท TypeScript ยท 38 stars ยท 4 forks ยท +1 stars in 24 hours ยท Trending score 0.55

  13. 13
    treeverse/dvc

    ๐Ÿฆ‰ Data Versioning and ML Experiments

    GitHub ยท Python ยท 15,978 stars ยท 1,344 forks ยท 0 stars in 24 hours ยท Trending score 0.52

  14. 14
    calkit/calkit

    A project framework, toolset, and web platform for collaborative, reproducible research.

    GitHub ยท Python ยท 63 stars ยท 18 forks ยท 0 stars in 24 hours ยท Trending score 0.47

  15. 15
    ClawBio/ClawBio

    ๐Ÿฆ– ClawBio - The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Open. Free.

    GitHub ยท Python ยท 1,185 stars ยท 293 forks ยท 0 stars in 24 hours ยท Trending score 0.42

  16. 16
    OpenBioSim/biosimspace

    An interoperable Python framework for biomolecular simulation.

    GitHub ยท Python ยท 177 stars ยท 22 forks ยท 0 stars in 24 hours ยท Trending score 0.39

  17. 17
    SPYfighting/my-academic-skills

    Research skills for Claude Code, Codex, and OpenCode.

    GitHub ยท Python ยท 24 stars ยท 0 forks ยท 0 stars in 24 hours ยท Trending score 0.35

  18. 18
    outerloop-science/outerloop

    Autoresearch agents that improve your benchmark: independent re-measurement, enforced budgets, results as pull requests

    GitHub ยท Python ยท 44 stars ยท 7 forks ยท 0 stars in 24 hours ยท Trending score 0.32

  19. 19
    NeoZorK/Monte-Neo

    Independent verifier for trading strategies written by AI agents and humans: catches look-ahead bias, hidden costs and overfitting. MCP server, CLI, GitHub Action, signed certificates.

    GitHub ยท Python ยท 10 stars ยท 1 forks ยท 0 stars in 24 hours ยท Trending score 0.32

  20. 20
    catalyst-cooperative/pudl-archiver

    A tool for capturing snapshots of public data sources and archiving them on Zenodo for programmatic use.

    GitHub ยท Python ยท 19 stars ยท 8 forks ยท 0 stars in 24 hours ยท Trending score 0.31

  21. 21
    anaconda/anaconda-project

    Tool for encapsulating, running, and reproducing data science projects

    GitHub ยท Python ยท 242 stars ยท 96 forks ยท 0 stars in 24 hours ยท Trending score 0.30

  22. 22
    humanfia/hma

    HMA (Humanize MLE Agents): alternating native coding agents over a shared workspace on MLE-bench โ€” paper experiment code

    GitHub ยท Python ยท 10 stars ยท 0 forks ยท 0 stars in 24 hours ยท Trending score 0.30

  23. 23
    gen740/Tsugumi

    A research workbench (macOS app and web UI) where you can run analyses drafted with AI as they are and verify them yourself. Environments are pinned with Nix, and every step of execution is recorded.

    GitHub ยท C++ ยท 12 stars ยท 1 forks ยท 0 stars in 24 hours ยท Trending score 0.30

  24. 24
    ScreamingFace/screamingface

    ScreamingFace is an open toolkit for composing fusions: ensembles, routers, cascades, or any other way of combining models, each graded as a single system against public benchmarks. Every fusion is written as one line and can be re-run for free or on your own API keys.

    GitHub ยท Python ยท 24 stars ยท 5 forks ยท 0 stars in 24 hours ยท Trending score 0.24