Stars
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
TokenSpeed is a speed-of-light LLM inference engine.
The agent that grows with you
Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
[NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
A Datacenter Scale Distributed Inference Serving Framework
🥢像老乡鸡🐔那样做饭。已添加2026年发布的《老乡鸡菜品溯源报告 2.0中新出现的菜品。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.
slime is an LLM post-training framework for RL Scaling.
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
SGLang is a high-performance serving framework for large language models and multimodal models.
My learning notes for ML SYS.
更新2008年版本的《上海交通大学生存手册》gitbook发布于https://survivesjtu.gitbook.io/survivesjtumanual/