AI coding agent, built for the terminal.

Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.

A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations)

The best ChatGPT that $100 can buy.

RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

Implement a reasoning LLM in PyTorch from scratch, step by step

Comprehensive PyTorch tutorial for learning and interview preparation - covers basics to advanced topics with hands-on examples

The AWS Provider enables Terraform to manage AWS resources.

An open-source AI agent that brings the power of Gemini directly into your terminal.

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!

aider is AI pair programming in your terminal

s1: Simple test-time scaling

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & RFT & Dynamic Sampling & Async Agent RL)

Official inference framework for 1-bit LLMs

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Command and Conquer: Generals - Zero Hour

Command and Conquer: Red Alert

Minimalistic large language model 3D-parallelism training

Train transformer language models with reinforcement learning.

A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!

Curated list of datasets and tools for post-training.

🤖 Fork me to try out Dependabot

Turn expensive prompts into cheap fine-tuned models