Ai4science Python Packages

paddleocr

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.

mineru

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

fhaviary

A language agent gym with challenging scientific tasks

mattersim

MatterSim: A deep learning atomistic model across elements, temperatures and pressures.

magic-pdf

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

terratorch

A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).

protenix

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

brainunit

Physical units and unit-aware mathematical system for general-purpose brain dynamics modeling.

saiunit

Unit-aware computations for AI-driven scientific computing, compatible with NumPy, JAX, PyTorch, CuPy, Dask, ndonnx.

evoscientist

🔬 Harness Vibe Research with Self-evolving AI Scientists

clio-agent

A science agent supporting any general AI agent in performing data management operations at scale. Builds upon the heritage of the IOWarp platform and proudly represents work done at Gnosis Research Center at Illinois Tech. Supported by NSF.

clio-kit

Bringing AI practically to science!

multimolecule

Accelerate Molecular Biology Research with Machine Learning

mineru-next-dev

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

langchain-paddleocr

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.

aidsorb

Python package for deep learning on porous materials and beyond.

mineru-selfhosted-mcp

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

molgen

Lightweight toolkit for de novo molecular generation: SMILES & SELFIES tokenizers, CharRNN / MolGPT / VAE models, training, sampling, and MOSES-style metrics.

intellifold

IntelliFold: A Controllable Foundation Model for General and Specialized Biomolecular Structure Prediction.

principia-ai

Principia extracts reusable principles, composes those principles into traceable research ideas, and helps researchers inspect why an idea may be worth testing.

crystalyse-ai

Intelligent Scientific Agent for Materials Design

iowarp-mcps

Open Source MCP Servers for Scientific Computing

fadoudou2

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.

buctoolkit

Batch-upscaled Catalysis Toolkit