TypeScript 排行榜

The Typescript MCP Framework

🤖️ Deploy GPT-4o ChatGPT on your WeChat within 2 steps! 两步在云端部署你的微信ChatGPT聊天机器人！🤖️

AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.

AI tutor powered by Theory-of-Mind reasoning

OpenCode extension manager with portable, isolated profiles. Your setup, anywhere.

A Model Context Protocol server for connecting Notion to MCP-compatible clients

Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI

TongFlow — Multimodal GenAI Studio

✨ ChatGemini 是一个基于 Google Gemini 的网页客户端，对标 ChatGPT 3.5，操作逻辑同 ChatGPT 3.5 一致，同时支持在聊天中上传图片，应用会自动调用 Gemini-Pro-Vision 模型进行识图。

Browser automation clicks buttons. OpenTabs calls APIs.

Lumina Note - A modern Markdown note-taking app with live preview, bidirectional links, and AI assistant

MCP server helping models to understand your Vite/Nuxt app better.

A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.

Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.

Mock everything your AI app talks to — LLM APIs, MCP, A2A, AG-UI, vector DBs, search. One package, one port, zero dependencies.

Expose Gemini CLI endpoints as OpenAI API with Cloudflare Workers

Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control

Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.

China's 1st enterprise multi-agent IT ops platform. LLM-powered auto-remediation for Zabbix/Prometheus. Docker deploy.

AI-powered StartUp Accelerator Engine built with Next.js, LangChain, PostgreSQL + pgvector. Upload, organize, and chat with documents. Includes predictive missing-document detection, role-based workflows, and page-level insight extraction.