Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~5000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓

🐧 Harness for RSI. Let AI Build AI

A kernel library written in tilelang

网文/小说写作 skill 包，覆盖长篇与短篇网络小说的扫榜、拆文、写作、去AI味、封面图全流程 | An all-in-one skill pack for long- and short-form web fiction.

👩🏿‍💻👨🏾‍💻👩🏼‍💻👨🏽‍💻👩🏻‍💻中国独立开发者项目列表 -- 分享大家都在做什么

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

一份图文并茂的保姆级教程：教你通过 VS Code + cc-Switch 优雅地在 Claude Code 中调用第三方大模型 API（如硅基流动），完美支持本地与 Remote - SSH 远程环境，低成本开启你的 Vibe Coding 之旅！🚀

An asynchronous streaming data management module for efficient post-training.

FastGithub 是 GitHub 加速神器，解决 GitHub 打不开、用户头像无法加载、releases 无法上传下载、git-clone、git-pull、git-push

Stable and Efficient Reinforcement Learning for Trillion-Parameter LLMs

Run more RL experiments. Wait less for GPUs.

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

MrlX: A Multi-Agent Reinforcement Learning Framework

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

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Twinkle✨: Training workbench to make your model glow.

OpenTinker is an RL-as-a-Service infrastructure for foundation models

A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

LLaMA Factory Document

A PyTorch native platform for training generative AI models

A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Train a 1B LLM with 1T tokens from scratch by personal

Implementation for FP8/INT8 Rollout for RL training without performence drop.

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

Reproduce R1 Zero on Logic Puzzle

Fully open reproduction of DeepSeek-R1