A Gym for Agentic LLMs

Verlog: A Multi-turn RL framework for LLM agents

JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️

An extremely fast Python type checker and language server, written in Rust.

A cache for AI agents to learn and replay complex behaviors.

Pydoll is a library for automating chromium-based browsers without a WebDriver, offering realistic interactions.

Dynamically creating multi-agent systems from a library of sub-agents

Reinforcement Learning example in C, playing tic tac toe

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

EgoNormia | Benchmarking Physical Social Norm Understanding in VLMs

The python library for real-time communication

Extra features for Python's JSON: comments, order, numpy, pandas, datetimes, and many more! Simple but customizable.

Our library for RL environments + evals

Simple RL training for reasoning

🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

A modern cookiecutter template for Python projects that use uv for dependency management

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

The fastest way to create an HTML app

SQL databases in Python, designed for simplicity, compatibility, and robustness.

Turn DataFrames Into PDF Reports

🧪🤖 Pytest plugin for OpenAI requests

[ICML 2025] ResearchTown: Simulator of Human Research Community

It's React, but in Python

generate release PRs based on the conventionalcommits.org spec