ai-scientist repositories
Trending repositories tagged ai-scientist, ranked by trending score. Updated daily.
-
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 · 57,924 stars · 5,080 forks · +264 stars in 24 hours · Trending score 4.59
-
2
ZJU-REAL/Polaris
Toward Autonomous Scientific Discovery
GitHub · Python · 267 stars · 40 forks · +15 stars in 24 hours · Trending score 2.12
-
3
synthetic-sciences/openscience
The open-source AI workbench for scientific research
GitHub · TypeScript · 4,404 stars · 554 forks · +9 stars in 24 hours · Trending score 2.05
-
4
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 · 263 stars · 20 forks · +1 stars in 24 hours · Trending score 1.68
-
5
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 0.94
-
6
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 · 1,077 stars · 108 forks · +1 stars in 24 hours · Trending score 0.91
-
7
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 · 2,103 stars · 231 forks · 0 stars in 24 hours · Trending score 0.62
-
8
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 · −1 stars in 24 hours · Trending score 0.51
-
9
worldbench/awesome-ai-auto-research
🔥 A Survey on AI Auto-Research
GitHub · HTML · 581 stars · 67 forks · 0 stars in 24 hours · Trending score 0.44
-
10
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 0.32
-
11
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 · 19 stars · 1 forks · 0 stars in 24 hours · Trending score 0.14
-
12
zjunlp/Mechanist
AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence
GitHub · Python · 82 stars · 8 forks · 0 stars in 24 hours · Trending score 0.08
-
13
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 0.05
-
14
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 · 354 stars · 54 forks · 0 stars in 24 hours · Trending score 0.04
-
15
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 0.04
-
16
foryourhealth111-pixel/Vibe-Skills
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
GitHub · Python · 3,808 stars · 344 forks · 0 stars in 24 hours · Trending score 0.02
-
17
cloudcell/gnosislab
A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.
GitHub · Python · 21 stars · 8 forks · 0 stars in 24 hours · Trending score 0.02
-
18
OpenNSWM-Lab/FAROS
A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
GitHub · Python · 3,044 stars · 390 forks · 0 stars in 24 hours · Trending score 0.00
-
19
zjunlp/SciAtlas
A Large-Scale Knowledge Graph for Automated Scientific Research
GitHub · Python · 171 stars · 16 forks · 0 stars in 24 hours · Trending score 0.00
-
20
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 · 505 stars · 43 forks · 0 stars in 24 hours · Trending score 0.00
-
21
InternScience/ResearchClawBench
🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
GitHub · Jupyter Notebook · 276 stars · 27 forks · 0 stars in 24 hours · Trending score 0.00
-
22
dualverse-ai/station
The Station is an open-world multi-agent environment where AI agents pursue autonomous scientific discovery and build a shared literature.
GitHub · Python · 193 stars · 16 forks · 0 stars in 24 hours · Trending score 0.00
-
23
openags/paper-search-mcp
MCP, CLI, Skills for searching and downloading academic papers from multiple sources like arXiv, PubMed, bioRxiv, etc.
GitHub · Python · 3,036 stars · 305 forks · 0 stars in 24 hours · Trending score 0.00
-
24
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 · 172 stars · 8 forks · 0 stars in 24 hours · Trending score 0.00