Verifiers for LLM Reinforcement Learning

A non-saturating, open-ended environment for evaluating LLMs in Factorio

A high-throughput and memory-efficient inference and serving engine for LLMs

The open source coding agent.

A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.

Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Democratizing Reinforcement Learning for LLMs

Harbor is a framework for running agent evaluations and creating and using RL environments.

Provider-agnostic, open-source evaluation infrastructure for language models

Train transformer language models with reinforcement learning.

Scaling Data for SWE-agents

mini-swe-agent-plus: a tiny (~100 LOC) GitHub issue fixer—now with a robust multi-line text edit tool.

🤗 smolagents: a barebones library for agents that think in code.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

SkyRL: A Modular Full-stack RL Library for LLMs

The Prime Intellect CLI provides a powerful command-line interface for managing GPU resources across various providers

Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Development repository for the Triton language and compiler

verl: Volcano Engine Reinforcement Learning for LLMs

Automatic evals for LLMs

Nano vLLM