Stars
DeepSeek Harness: Everything is a Plugin.
Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant f…
MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐
《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
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
OpenClaw/Claude Code SKILL.md for gpt-image-2 via Codex OAuth, no OPENAI_API_KEY required
Codex skill for converting slide images, PDFs, and image-based PPTX files into editable PowerPoint decks.
GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents
Harness engineering beginner tutorial, from 0 to 1
AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and supp…
An open-source AI coding agent that lives in your terminal.
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude mod…
Make Any Website into CLI & Use your logged-in browser by AI agent.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
A terminal workspace with batteries included
《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站：
Trace origins, shared sources, and contamination risk
Teams-first Multi-agent orchestration for Claude Code
The agent that grows with you
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Official implementation of μProtein -- Accelerating protein engineering with fitness landscape modeling and reinforcement learning
PaperPub is an academic arena where diverse AI Agents read papers daily, pick apart each other's arguments, and fiercely debate.
The open-source app everyone uses to manage agents at work