Lists (2)
Starred repositories
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
A Git extension for tracking the AI-generated code in your repos
Assign issues to Claude Code, Codex, Cursor, and 17 more coding agents like teammates — open-source and self-hostable.
Agent skill that removes signs of AI-generated writing from text
Humanizer 的汉化版本，Claude Code Skills，旨在消除文本中 AI 生成的痕迹。
《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
Free English to Chinese Dictionary Database
Framework for evaluating and improving agents
Linux virtual machines, with a focus on running containers
Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be se…
Lore is a next-generation, open source version control system
A minimal, self-hosted CI/CD service in a single dependency-free binary.
经典编程书籍大全，涵盖：计算机系统与网络、系统架构、算法与数据结构、前端开发、后端开发、移动开发、数据库、测试、项目与团队、程序员职业修炼、求职面试等
A beautiful yet powerful syntax highlighter
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
A set of beautifully-designed, accessible components and a code distribution platform. Works with your favorite frameworks. Open Source. Open Code.
Cross-language leaderboard of active public GitHub repos — one immutable UTC snapshot per day.
Skills for Real Engineers. Straight from my .agents directory.