Stars
Reproducing and studying RL algorithms for LLM agents, including PPO, GRPO, GSPO, DAPO, OPD and beyond.
OpenReadest 是基于 Readest 的非官方分支，专注于保留本地阅读功能，同时增加 WebDAV 同步支持，专为私有云或自托管 WebDAV 场景设计。
A fully functional AI Agent desktop client that supports Webui access and can be creatively customized and expanded!
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
An open source alternative to raycast, in rust!!
Phaser is a fun, free and fast 2D game framework for making HTML5 games for desktop and mobile web browsers, supporting Canvas and WebGL rendering.
Orchestrate multiple coding agents from desktop and mobile
Bridge the gap between photo and video color grading. Accurately apply any creative LUT to your RAW files with this tool.
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
A local-first, AI-enhanced novel library and reader for personal homelabs. Another Calibre alternative.
Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
LLM algorithm practice lab with theory, solutions, and test cases.《大模型算法与系统教程》面向大模型入门到进阶的算法实战教程，覆盖原理讲解、答案解析、测试用例与 CUDA/Triton 实战。
A tutorial on modern GPU programming for machine learning systems
🐸 Read Frog - Open Source Immersive Translate | 🐸 陪读蛙 - 开源沉浸式翻译
Open reimplementation of Sakana Fugu — the 'one model to command them all' LLM orchestrator. Read → run → train → serve.
这是我的强化学习笔记
Personal deep learning study notes and tutorial-style notebooks
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
WPS Skills | WPS Office 智能助手 | WPS Office AI Assistant
Local-first Agent Skill for building a user-owned Tasteprint profile and using it for better, privacy-aware product recommendations.
A minimal, accessible and SEO-friendly Astro blog theme.