Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
scientific-agent-skills
SkillsTurn 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.
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git -
claude-scientific-writer
Agents & frameworksA general purpose scientific writer
git clone https://github.com/K-Dense-AI/claude-scientific-writer.git -
open-science
SkillsThe open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.
git clone https://github.com/aipoch/open-science.git -
smol-training-playbook
Tools & appsHugging Face space by HuggingFaceTB
HuggingFaceTB/smol-training-playbook -
openscience
AI repositoriesThe open-source AI workbench for scientific research
git clone https://github.com/synthetic-sciences/openscience.git -
scientific_papers
Datasets & benchmarksHugging Face dataset by armanc
armanc/scientific_papers -
robot-learning-tutorial
Tools & appsHugging Face space by lerobot
lerobot/robot-learning-tutorial -
Light-Science
SkillsA research workflow skill pack connecting literature, experiments, figures, writing, memory and project coordination.
git clone https://github.com/Light0305/Light-Science.git -
ScientificFigureLibrary
MCP serversLocal-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.
git clone https://github.com/xuzhougeng/ScientificFigureLibrary.git -
ai-for-grant-writing
AI repositoriesA curated list of resources for using LLMs to develop more competitive grant applications.
git clone https://github.com/eseckel/ai-for-grant-writing.git -
FAROS
Agents & frameworksA blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
git clone https://github.com/OpenNSWM-Lab/FAROS.git -
Awesome-Scientific-LLM-Benchmarks
Datasets & benchmarksA curated, accuracy-first list of benchmarks for evaluating LLMs on scientific reasoning and discovery — math, physics, chemistry, materials, biology, and agentic science.
git clone https://github.com/subinium/Awesome-Scientific-LLM-Benchmarks.git -
Plato-Scientific-Research-Autonomous-Agent
Agents & frameworksMulti-agent AI scientist that turns experimental data into > publication-ready research papers.
git clone https://github.com/Eldergenix/Plato-Scientific-Research-Autonomous-Agent.git -
paper-qa
AI repositoriesHigh accuracy RAG for answering questions from scientific documents with citations
git clone https://github.com/Future-House/paper-qa.git -
figures4papers
AI repositoriesMy Python scripts to make high-quality figures for publications in top AI conferences and journals.
git clone https://github.com/ChenLiu-1996/figures4papers.git -
llm-srbench
Agents & frameworks[ICML2025 Oral] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
git clone https://github.com/deep-symbolic-mathematics/llm-srbench.git -
scientific-writing-skills
SkillsSix Claude Agent Skills for scientific writing, distilled from Stanford's Writing in the Sciences (Kristin Sainani). Edit prose, structure an IMRaD manuscript, run the writing process, handle peer review, draft grants, and write for general audiences.
git clone https://github.com/dvdsosa/scientific-writing-skills.git -
OpenQuantum
MCP serversOpen-source quantum Agent workspace with a desktop client, Web UI, messaging, Qiskit/MCP tools, and scientific validation
git clone https://github.com/xi-zhao/OpenQuantum.git -
SciAgent-Skills
Skills197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon.
git clone https://github.com/jaechang-hits/SciAgent-Skills.git -
LLM-SR
Agents & frameworks[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models
git clone https://github.com/deep-symbolic-mathematics/LLM-SR.git -
polish-sci-figures
SkillsScientific figure toolkit and Figure Studio: editable templates, local statistics, multi-panel editing and SVG/PNG/TIFF export, with skills for Codex and Claude. | 科研绘图与组图编辑:模板作图、统计分析、精修排版及高清导出。
git clone https://github.com/zhoy0409-debug/polish-sci-figures.git -
research-writing-skill
Prompts🎓 AI 科研论文写作助手 - 30 个 Prompt 模板覆盖论文写作全流程。支持中英文翻译、润色、文献综述、投稿回复、基金申请等。
git clone https://github.com/alfonso0512/research-writing-skill.git -
arxiv-complete
Datasets & benchmarksHugging Face dataset by secemp9
secemp9/arxiv-complete -
ai-draw
AI repositoriesCreate and edit drawings through conversation.
git clone https://github.com/bugkeep/ai-draw.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.