Stars
MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
Environments for LLM Reinforcement Learning
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Build, evaluate and train General Multi-Agent Assistance with ease
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Steering LLM Thinking with Budget Guidance
Train transformer language models with reinforcement learning.
Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Post-training with Tinker
Access to Anthropic's safety-first language model APIs in TypeScript
Browse, search, export, and share your entire Cursor AI chat history
A modular graph-based Retrieval-Augmented Generation (RAG) system
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Go (golang) calendar library for dealing with holidays and work days
The ultimate LLM/AI application development framework in Golang.
Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.
Making large AI models cheaper, faster and more accessible
A self hosted virtual browser that runs in docker and uses WebRTC.
An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.
Use your Mac trackpad as a weighing scale
Textbook on reinforcement learning from human feedback