Skip to content
#

AI for science

Star

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.

Here are 293 public repositories matching this topic...

Language: All
Filter by language
All 293 Python 182 Jupyter Notebook 24 HTML 11 TypeScript 9 JavaScript 7 TeX 5 Shell 4 Rust 3 Arc 1 C++ 1
Sort: Most stars
Sort options
Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated
open-science

aipoch / open-science

Star 4.1k

AIPOCH Open-Science is an open-source, local-first, model-agnostic AI research workbench for macOS, Windows, and Linux, with scientific agents, Python/R notebooks, data connectors, and reproducible provenance.

electron desktop-app python windows macos linux bioinformatics r reproducible-research mcp open-science ai-research research-software model-agnostic local-first scientific-ai ai-for-science ai-workbench research-workbench claude-science-alternative
  • Updated Sep 11, 2026
  • TypeScript

OpenNSWM-Lab / FAROS

Star 3k

A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.

multi-agent paper-writing academic-writing scientific-workflow workflow-orchestration paper-generation academic-research scientific-discovery automated-research autonomous-research ai4science ai-for-science research-automation llm-agents research-agent agentic-workflow ai-scientist research-workflow research-orchestration autoresearch
  • Updated Sep 5, 2026
  • Python

ai4s-research / open-science

Star 1.6k

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.

desktop-app windows macos linux reproducible-research mcp open-science scientific-research tauri local-first ai-agent research-tools ai-for-science ai-scientist ai4s research-workbench claude-science claude-science-alternative open-science-desktop claude-science-desktop-alternative
  • Updated Sep 11, 2026
  • TypeScript

xuzhougeng / wisp-science

Star 1.1k

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.

desktop-app python rust bioinformatics reproducible-research mcp computational-biology scientific-computing rstats tauri research-assistant scientific-workflow local-first ai-assistant ai-agent ai4science llm ai-for-science model-context-protocol agent-skills
  • Updated Sep 11, 2026
  • Rust

atomicarchitects / equiformer_v2

Star 351

[ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

machine-learning deep-learning molecular-dynamics pytorch computational-chemistry computational-physics drug-discovery materials-science force-fields geometric-deep-learning graph-neural-networks interatomic-potentials ai-for-science e3nn equivariant-neural-networks equivariant-graph-neural-network catalyst-design equiformer
  • Updated Apr 10, 2026
  • Python
Followers
20 followers
Website
github.com/topics/ai-for-science

Related topics

ai bioinformatics chemistry data-science deep-learning machine-learning physics simulation