#ai4science Repositories
Discover 21 active open source GitHub repositories tagged with #ai4science, accumulating 203,254 total stars (averaging 9,678 stars per project). Leading this topic is PaddlePaddle/PaddleOCR with 92,972 stars.
21 repositories total
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
Graphormer is a general-purpose deep learning backbone for molecular modeling.
A curated list of awesome AI tools, libraries, papers, datasets, and frameworks that accelerate scientific discovery โ from physics and chemistry to biology, materials, and beyond.
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
Principia extracts reusable principles, composes those principles into traceable research ideas, and helps researchers inspect why an idea may be worth testing.
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.
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
๐๐๐A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.
๐ A ranked list of awesome atomistic machine learning projects โ๏ธ๐งฌ๐.
freephdlabor: customizing personalized multiagent systems that research 24/7 on your own scientific problem
A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (EMNLP'24)
[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.
MatterSim: A deep learning atomistic model across elements, temperatures and pressures.
Frequently Asked Questions
What is the most popular #ai4science repository on GitHub?
The top ranked open source #ai4science project on GitHub is PaddlePaddle/PaddleOCR with 92,972 stars. Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Which programming languages are most used in #ai4science repositories?
Among the top ranked #ai4science projects on GitHub, the most common programming languages are Python, Rust, Rich Text Format, Jupyter Notebook.
How is the #ai4science repository ranking calculated?
We track 21 active open source repositories tagged with #ai4science (500+ stars), totaling 203,254 stars with an average of 9,678 stars per repository. Rankings update daily from the GitHub API.