A curated list of awesome AI tools, libraries, papers, datasets, and frameworks that accelerate scientific discovery — from physics and chemistry to biology, materials, and beyond.
-
Updated
Jun 19, 2026
AI for science is the application of machine learning and artificial intelligence methods to accelerate research and discovery across scientific domains. It encompasses work in protein structure prediction, climate modeling, drug discovery, materials design, and particle physics, among others.
Rather than replacing traditional scientific methods, AI for science augments them by learning patterns from experimental and simulation data to generate hypotheses, design experiments, and build fast surrogate models. Landmark examples include AlphaFold for protein structure prediction, GraphCast for weather forecasting, and FermiNet for quantum chemistry.
A curated list of awesome AI tools, libraries, papers, datasets, and frameworks that accelerate scientific discovery — from physics and chemistry to biology, materials, and beyond.
Democratizing AI scientists with ToolUniverse
AgentSociety 2 is a modern, LLM-native agent simulation platform designed for social science research and experimental design. It provides a flexible framework for creating and managing intelligent agents in simulated environments.
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Scholar All-In-One: A research infrastructure for AI agents
Any research. One Claw. 🦞 From any materials to research with fully autonomous & skill-driven researcher.
❓Curie: Automated and Rigorous Scientific Experimentation with AI Agents
A Collection of Awesome Large Weather Models (LWMs) | AI for Earth (AI4Earth) | AI for Science (AI4Science)
[ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
Scientific machine learning (SciML) benchmarks, AI for science, and (differential) equation solvers. Covers Julia, Python (PyTorch, Jax), MATLAB, R
The official implementation of 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction (ICLR 2023)
[ICLR 2024] Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models
[updating] Chinese Medical Dataset 致力于详细整理所有现有中文医学数据集,包括详细的数据汇总、数据示例、下载链接等。
[ICLR 2023 Spotlight] Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.
Automated Hypothesis Testing with Agentic Sequential Falsifications
Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code
[NeurIPS'24] Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling
Learning the language of protein-protein interactions
Terminal-Bench-Science: Evaluating AI Agents on Complex Real-World Scientific Workflows in the Terminal