Starred repositories
HarnessX is a harness foundry: forge any number of agent harnesses from reusable processors and bundles, pair each with any model, and evolve them through training.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Create beautiful slides on the web using a coding agent's frontend skills
Latest Advances on Agentic AI & AI Agents for Healthcare
A股全栈数据工具包 · 十一层架构 · 54端点 · 19数据源 · 零鉴权 | Full-stack China A-share data toolkit for AI agents — 11 layers, 54 endpoints, 19 sources, zero-auth
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
AI agents running research on single-GPU nanochat training automatically
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
An official Qdrant Model Context Protocol (MCP) server implementation
Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code!
An agentic skills framework & software development methodology that works.
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
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, …
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
Neo4j Graph Data Scientist Agent (MCP Server & Skills)
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Run Windows apps such as Microsoft Office/Adobe in Linux (Ubuntu/Fedora) and GNOME/KDE as if they were a part of the native OS, including Nautilus integration. Hard fork of https://github.com/Fmst…
"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"
📄 Easily create your resume with Markdown on VSCode / Typora / Obsidian
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Open Data Platform for analysts, quants and AI agents.