Starred repositories
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
A project implementing various agentic RL based on the Slime post-training framework
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
原汁原昧 Claude Code 可运行,可构建, 可调试版; Typescript 类型全修复; 企业级可靠性; 安全无毒, lock 文件保真, 可直接 bun i; bun run dev 启动
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
OpenClaw-RL: Train any agent simply by talking
Kimi Agent SDK provides a programmatic interface to interact with the Kimi CLI
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing
A user-friendly & efficient knowledge distillation framework for LLMs, supporting off-policy, on-policy (OPD), cross-tokenizer, multimodal, and on-policy self-distillation.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Accelerating MoE with IO and Tile-aware Optimizations
Machine Learning Engineering Open Book