Research Python Packages

rouge-score

Google Research

yacs

YACS -- Yet Another Configuration System

sb3-contrib

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

scann

Google Research

gpt-researcher

An autonomous agent that conducts deep research on any data using any LLM providers

pypartmc

Python (and C++) interface to PartMC with Jupyter/Python, Julia and Matlab examples

arxiv-mcp-server

A Model Context Protocol server for searching and analyzing arXiv papers

pymeasure

Scientific measurement library for instruments, experiments, and live-plotting

khoj

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

tableone

Create "Table 1" for research papers in Python

openpmd-api

:floppy_disk: C++ & Python API for Scientific I/O

khoj-assistant

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

pymbar

Python implementation of the multistate Bennett acceptance ratio (MBAR)

rtdl-num-embeddings

(NeurIPS 2022) On Embeddings for Numerical Features in Tabular Deep Learning

research-hub-pipeline

AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, MCP, REST, and dashboard.

research-pipeline

Deterministic stage-based pipeline for searching, screening, downloading, converting, and summarizing academic papers. CLI + MCP server.

rtdl-revisiting-models

(NeurIPS 2021) Revisiting Deep Learning Models for Tabular Data

rdagent

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report

catalyst

Accelerated deep learning R&D

optax-shampoo

Google Research

carla

Open-source simulator for autonomous driving research.

impactx-noacc

ImpactX: the next generation of the IMPACT-Z beam dynamics code

wntr

An EPANET compatible python package to simulate and analyze water distribution networks under disaster scenarios.

dallinger

Laboratory automation for the behavioral and social sciences; human culture on a chip.