GitHub AI/LLM/Agent Trending
AI · · 1 min read
GitHub AI/LLM/Agent Trending Repos (May 25-26, 2026)
topic:AI
- UditAkhourii/adhd ⭐39 - ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude Agent SDK. Fans out parallel diverge
- machinesoul11/anti-sycophant-ai-agent-skills ⭐25 - Skills that get AI assistants to stop agreeing with bad product ideas by default — pressure-test premises, separate hobb
- Saito-Sakuya/CandyCraft ⭐21 - Candy Craft：一个可视化 AI 生图提示词优化工具，支持画板编排、相机布光和双模式 API（后台托管/用户自定义），可直接部署到 Cloudflare Pages。
- code-yeongyu/lazycodex ⭐20 - LazyCodex: Codex for no-brainers. You don't need to think. Just prompt with ultrawork.
- pguso/mcp-from-scratch ⭐12 - Learn Model Context Protocol (MCP) from scratch in plain Node.js. Build a working MCP server step by step with zero blac
topic:LLM
- UditAkhourii/adhd ⭐39 - ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude Agent SDK. Fans out parallel diverge
- pguso/mcp-from-scratch ⭐12 - Learn Model Context Protocol (MCP) from scratch in plain Node.js. Build a working MCP server step by step with zero blac
- AndrewDzzz/browser-harness-bidi ⭐5 - WebDriver BiDi-first browser harness for AI agents, inspired by browser-use/browser-harness.
- BioTender-max/awesome-bio-agent-skills ⭐4 - A curated collection of AI agent skills for biomedical research, covering genomics, proteomics, single-cell analysis, cl
- lucasmullikin/ModelStatus ⭐3 - A macOS menu bar app for monitoring local AI model servers — Ollama, LM Studio, vLLM, MLX, llama.cpp, and any OpenAI-com
topic:Agent
- lambda765/smzdm_bot ⭐2 - 什么值得买智能推送机器人，可根据用户喜好、库存状态等自动筛选推送至飞书
- shakyarudransh15-lab/Maverick---Soverign-AI-Agent ⭐2 - Maverick AGI v2.5 – a fully offline, terminal‑first personal AI assistant that runs locally on your machine. It speaks,
- Li13576/business-research-skills ⭐1 - 专为商科生设计的 学术工具套件一条流水线：找文献 → 整理文献 → 跑 Stata 回归 → 写论文 → 审稿 → 定稿，全程自动调度。可直接串接 Stata MCP，让 ai 能操作 Stata 执行量化分析、生成结果表格、记录研究日志，
- gokborayilmaz/chatgpt-llms-evaluation-sandbox ⭐1 - An AI-powered automated benchmark team designed to dynamically generate accurate dataset test-suites and automatically e
- zy-tjx/Agent-Runtime ⭐1 - 本项目并非开发“聊天机器人”或“普通学习助手”，而是构建一个可治理的单 Agent Runtime 实验平台，用于系统性训练和理解 Agent Engineering 的核心能力
Highlights
- UditAkhourii/adhd (⭐39) - Tree-of-thought coding agent skill with pruning, built on Claude Agent SDK
- pguso/mcp-from-scratch (⭐12) - MCP server tutorial in plain Node.js
- machinesoul11/anti-sycophant-ai-agent-skills (⭐25) - AI agent skills that resist sycophancy