ai-scientist repositories

Trending repositories tagged ai-scientist, ranked by trending score. Updated daily.

  1. 1
    K-Dense-AI/scientific-agent-skills

    Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

    GitHub · Python · 58,074 stars · 5,085 forks · +178 stars in 24 hours · Trending score 4.38

  2. 2
    openags/paper-search-mcp

    MCP, CLI, Skills for searching and downloading academic papers from multiple sources like arXiv, PubMed, bioRxiv, etc.

    GitHub · Python · 3,144 stars · 308 forks · +103 stars in 24 hours · Trending score 3.22

  3. 3
    ruc-datalab/DeepAnalyze

    DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师,自动分析大量数据,一键生成专业分析报告!

    GitHub · Python · 4,833 stars · 757 forks · +53 stars in 24 hours · Trending score 2.87

  4. 4
    synthetic-sciences/openscience

    The open-source AI workbench for scientific research

    GitHub · TypeScript · 4,411 stars · 555 forks · +13 stars in 24 hours · Trending score 2.19

  5. 5
    brycewang-stanford/Free-Research-Crew

    Free-Research-Crew (免费助研团): a crew of RA agents that co-writes CS & social-science papers with real experiments and data modeling, built on a curated hub of 6,000+ research skills. | 多智能体助研团队,协作完成计算机与社科论文。

    GitHub · Python · 267 stars · 20 forks · +3 stars in 24 hours · Trending score 2.00

  6. 6
    wanshuiyin/Anti-Autoresearch

    Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.

    GitHub · Python · 182 stars · 9 forks · +10 stars in 24 hours · Trending score 1.74

  7. 7
    yogsoth-ai/de-anthropocentric-research-engine

    Give an AI a research direction: it runs literature synthesis, gap validation, hypothesis formation and experiment design itself. 267 markdown skills form a research graph: 51 operations built from 216 atomic steps, any order, explicit backtracking; the plan is approved before it runs and interrupted runs resume. npx install, no runtime, no API key

    GitHub · 516 stars · 44 forks · +11 stars in 24 hours · Trending score 1.71

  8. 8
    yenanjing/awesome-ai-for-science

    A curated list of awesome projects using AI to automate scientific research — AI Scientist, autonomous research agents, paper writing, hypothesis generation, and more.

    GitHub · Python · 15 stars · 9 forks · +5 stars in 24 hours · Trending score 1.53

  9. 9
    worldbench/awesome-ai-auto-research

    🔥 A Survey on AI Auto-Research

    GitHub · HTML · 582 stars · 67 forks · +4 stars in 24 hours · Trending score 1.36

  10. 10
    Omni-Scientist/OmniScientist

    An Omni-Modal, Omni-Discipline AI Scientist

    GitHub · TypeScript · 175 stars · 22 forks · +3 stars in 24 hours · Trending score 1.06

  11. 11
    zjunlp/SciAtlas

    A Large-Scale Knowledge Graph for Automated Scientific Research

    GitHub · Python · 174 stars · 16 forks · +3 stars in 24 hours · Trending score 0.90

  12. 12
    ZJU-REAL/Polaris

    Toward Autonomous Scientific Discovery

    GitHub · Python · 269 stars · 40 forks · 0 stars in 24 hours · Trending score 0.85

  13. 13
    mikamikasuki/forest

    FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence

    GitHub · Python · 355 stars · 57 forks · +1 stars in 24 hours · Trending score 0.72

  14. 14
    THU-Team-Eureka/EurekAgent

    EurekAgent: an autonomous research system for metric-driven tasks, built with Claude Code. Define the problem and metric. Get breakthrough results.

    GitHub · Python · 87 stars · 6 forks · 0 stars in 24 hours · Trending score 0.51

  15. 15
    xuzhougeng/wisp-science

    Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.

    GitHub · Rust · 1,080 stars · 110 forks · 0 stars in 24 hours · Trending score 0.50

  16. 16
    ai4s-research/open-science

    Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.

    GitHub · TypeScript · 2,120 stars · 233 forks · 0 stars in 24 hours · Trending score 0.48

  17. 17
    InternScience/SGI-Bench

    Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

    GitHub · Python · 173 stars · 4 forks · 0 stars in 24 hours · Trending score 0.42

  18. 18
    outerloop-science/outerloop

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

    GitHub · Python · 44 stars · 7 forks · 0 stars in 24 hours · Trending score 0.25

  19. 19
    openags/Awesome-AI-Scientist-Papers

    A collection of resources and papers on AI Scientist / Robot Scientist

    GitHub · 181 stars · 14 forks · 0 stars in 24 hours · Trending score 0.21

  20. 20
    systemind-team/Runtime-AI-Scientist

    Runtime AI Scientist (formerly RAC AI Scientist): official code for "Can AI Scientists Coordinate at Runtime?" (arXiv 2610.00980). Runtime Agent Coordination (RAC) for multi-agent AI scientists such as ARK, Agent Laboratory, and EvoScientist, evaluated on ResearchClawBench.

    GitHub · Python · 12 stars · 4 forks · 0 stars in 24 hours · Trending score 0.19

  21. 21
    allenai/novelty-eval

    Benchmark and controlled study of LLM-based novelty judges for research ideas. Code and data for "Old Ideas, Novel Problems" (arXiv 2610.02022)

    GitHub · Python · 22 stars · 1 forks · 0 stars in 24 hours · Trending score 0.14

  22. 22
    guy915/open-co-scientist

    An open-source recreation of AI Co-Scientist: a multi-agent scientific research harness.

    GitHub · Python · 14 stars · 0 forks · 0 stars in 24 hours · Trending score 0.08

  23. 23
    principia-ai/PhysGym

    A benchmark suite for evaluating LLM-based interactive scientific reasoning.

    GitHub · Python · 103 stars · 14 forks · 0 stars in 24 hours · Trending score 0.04

  24. 24
    OpenLAIR/dr-claw

    A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power.

    GitHub · JavaScript · 1,199 stars · 143 forks · 0 stars in 24 hours · Trending score 0.02