Stars
江山时序 · 中国历史交互地图时间轴 (403 BCE – Present) | Interactive Historical Atlas of China across 18 dynasties, 198 territory snapshots, ancient-to-modern place genealogy & classical poetry routes
AI 解说大师 — Agent skill;封装 narrator-ai-cli 供 Claude/Codex 等工具调用
DeepSeek Harness: Everything is a Plugin.
You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/O…
Make humans and AI agents work as one team — open-source and self-hostable.
Mastra is the modern TypeScript framework for AI-powered applications and agents.
Run Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime, and a run only counts as done when checks it didn't write pass. Cross-engine fan-out, councils, session handoff, spe…
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
Terminal in browser over http/https. (Ajaxterm/Anyterm alternative, but much better)
A toolbox for building web applications with editors utilizing language servers.
⚙️ Devtools for debugging Vue.js applications.
A lightweight, extendable front-end developer tool for mobile web page.
📦 Workbox: JavaScript libraries for Progressive Web Apps
🧠 Curated collection of system prompts for top AI tools. Perfect for AI agent builders and prompt engineers. Incuding: ChatGPT, Claude, Perplexity, Manus, Claude-Code, Loveable, v0, Grok, same new,…
Python tool for converting files and office documents to Markdown.
Vue Flow has a new home! We just joind xyflow and you can find us over there from now on.
React Flow | Svelte Flow | Vue Flow - Powerful open source libraries for building node-based UIs with React (https://reactflow.dev), Svelte (https://svelteflow.dev) and Vue (https://vueflow.dev). R…
[Not maintained] Axios plugin that intercepts failed requests and retries them whenever possible
Parlant is an open platform for building customer-facing chat agents with AI. Describe how the agent should behave, and your coding agent implements it for you.
FlashMLA: Efficient Multi-head Latent Attention Kernels