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.

fhaviary

A language agent gym with challenging scientific tasks

mineru

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

mattersim

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

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.

terratorch

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

magic-pdf

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

evoscientist

🔬 Harness Vibe Research with Self-evolving AI Scientists

clio-kit

Bringing AI practically to science!

brainunit

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

protenix

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

rapmat

Rapid materials discovery in the terminal

saiunit

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

multimolecule

Accelerate Molecular Biology Research with Machine Learning

openai4s

Open-source AI agent for scientific research. Analyze data in Python/R with Claude, GPT, Gemini, and more.

psrn

[𝐍𝐚𝐭𝐮𝐫𝐞 𝐂𝐨𝐦𝐩𝐮𝐭𝐚𝐭𝐢𝐨𝐧𝐚𝐥 𝐒𝐜𝐢𝐞𝐧𝐜𝐞] ⚡️ PSE/PSRN: Fast and efficient symbolic expression discovery through parallelized symbolic enumeration. Evaluates millions of expressions simultaneously on GPU with automated subtree reuse.

tensormesh-fem

A fast, differentiable, JIT-free, debugging-friendly finite element library for PyTorch.

mineru-selfhosted-mcp

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

iowarp-mcps

Bringing AI practically to science!

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.

aidsorb

Python package for deep learning on porous materials and beyond.

crystalyse-ai

Intelligent Scientific Agent for Materials Design

buctoolkit

Batch-upscaled Catalysis Toolkit

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.