Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
Local-first memory layer for CLI agents. Indexes Claude Code, Codex CLI, and Cursor session histories into SQLite + FTS5 — searchable from a CLI, TUI, or MCP server so your next agent session can...
ChatCrystal is a local-first AI PKM app for developers who solve real problems with Claude Code, Cursor, Codex CLI, Trae, and GitHub Copilot.
directory for Awesome MCP Servers
The AI agentic designer — open-source React design system + MCP that lets Claude, Codex, Cursor & Gemini build production UI in minutes. No AI slop.
GCO is a platform that spins up EKS Auto Mode clusters across AWS regions, wired together with Global Accelerator for low-latency routing.
A local-first Playwright test automation toolkit for AI coding agents (Cursor, Claude Code, Copilot), with MCP tools for codegen, browser control, and recordings.
Open security engineering for code written by humans and AI agents. Discover. Repair. Verify.
English Français Deutsch Español 日本語 한국어 繁體中文 简体中文
Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection, session harvesting into memories. Local-first.
An MCP server for exploring Israeli government open data (data.gov.il) — with built-in interactive visualizations powered by MCP Apps.
Real reap --agent output, run against a generated sample stack ( hero-fixture.sh ) — not anyone's install. The numbers further down are measured on mine.
AgentStack is a production-grade multi-agent framework built on Mastra, delivering 50+ enterprise tools, 25+ specialized agents, and A2A/MCP orchestration for scalable AI systems.
Agent Skills
你有没有遇到过这样的情况：换了老师之后，新老师讲的你怎么都听不懂？或者毕业了，再也没有人能像那个老师一样给你讲明白？
43 projects · 8 categories · End-to-end AI scientists · Experiment loops · Research co-pilots · Skill packs · Paper tools · Benchmarks
![Very Good Ventures][very_good_ventures_link_dark] ![Very Good Ventures][very_good_ventures_link_light]
它把角色卡、会话记忆、知识库、成员目录、技能系统、模型接入、Web Console，以及 OpenClaw 兼容 skill runtime 都收敛在同一个服务里；NapCat / OneBot 只负责 QQ 协议和消息收发。
上传你和 crush 的聊天记录，AI 模拟 ta 的性格，你在安全沙盒里反复练习——找到真诚又有效的沟通方式。 Upload your chat history with your crush. AI simulates their personality. Practice in a safe sandbox until you find your voice.
让你的 coding agent 的技能,从每一次真实会话里自我进化——你只管写代码。
- 与 是 skill 模式（被支持 Skills 的 IDE 加载执行），仅依赖可读的小程序源码目录 - 是独立的 Node 工程（含 CLI / Web UI），依赖 Node ≥ 18.17
is an open set of skills for the : proven instructions, workflows, and examples that help AI agents work with Spring Boot projects predictably.
A Claude Code skill for prompting Claude Fable 5 to orchestrate a build cheaply — Fable architects, Opus 4.8 executes.
Autofish gives any agent a stable, explicit, and observable Android execution layer: inspect the screen, act through stable refs instead of brittle coordinates, verify outcomes after every step, and...
微信读书前几天上了一个官方 AI skill（weread.qq.com/r/weread-skills），把书架、笔记、阅读统计、推荐 6 件事开放给 AI。能力很强，但它只是「自然语言包装的搜索接口」——你让它推荐书，它不会去看你已经读过什么，常把你笔记 68 条的书又当新书推回来给你。
For engineers who want agents shipping code without a human in the loop.