[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-related-zh-naman-sharma12345-kimo":3},{"items":4,"total":103,"page":104,"pageSize":105},[5,32,46,63,86],{"slug":6,"name":7,"categorySlug":8,"summary":9,"description":9,"categoryName":10,"sourceUrl":11,"homepageUrl":-1,"downloadUrl":12,"cliCommand":-1,"primaryLanguage":-1,"license":13,"stars":14,"forks":15,"trendScore":16,"qualityScore":17,"supportedClients":18,"clients":21,"tags":29,"installCommand":-1,"configSnippet":-1,"useCases":30,"updatedAt":31},"punkpeye-awesome-mcp-servers","punkpeye\u002Fawesome-mcp-servers","devtools","ray.run – from idea to a production-grade MCP server in under a minute! 🦜","开发工具","https:\u002F\u002Fgithub.com\u002Fpunkpeye\u002Fawesome-mcp-servers","https:\u002F\u002Fgithub.com\u002Fpunkpeye\u002Fawesome-mcp-servers\u002Farchive\u002FHEAD.zip","MIT",96334,17600,100,79,[19,20],"claude-desktop","vscode",[22,26],{"slug":19,"name":23,"summary":24,"count":25},"Claude Desktop","支持本地 MCP 配置的桌面客户端。",0,{"slug":20,"name":27,"summary":28,"count":25},"VS Code","可用 MCP Server 支持编程和本地自动化的编辑器生态。",[8,13],[],"2026-08-14T05:27:24.263802",{"slug":33,"name":34,"categorySlug":8,"summary":35,"description":35,"categoryName":10,"sourceUrl":36,"homepageUrl":-1,"downloadUrl":37,"cliCommand":-1,"primaryLanguage":-1,"license":13,"stars":38,"forks":39,"trendScore":16,"qualityScore":40,"supportedClients":41,"clients":42,"tags":43,"installCommand":-1,"configSnippet":-1,"useCases":44,"updatedAt":45},"hkuds-nanobot","hkuds\u002Fnanobot","English | 简体中文 | 繁體中文 | Español | Français | Bahasa Indonesia | 日本語 | 한국어 | Русский | Tiếng Việt Discord · X · WeChat \u002F Feishu","https:\u002F\u002Fgithub.com\u002Fhkuds\u002Fnanobot","https:\u002F\u002Fgithub.com\u002Fhkuds\u002Fnanobot\u002Farchive\u002FHEAD.zip",49037,8630,75,[],[],[8,13],[],"2026-08-19T05:48:15.579337",{"slug":47,"name":48,"categorySlug":8,"summary":49,"description":50,"categoryName":10,"sourceUrl":51,"homepageUrl":-1,"downloadUrl":52,"cliCommand":-1,"primaryLanguage":-1,"license":53,"stars":54,"forks":55,"trendScore":16,"qualityScore":56,"supportedClients":57,"clients":58,"tags":60,"installCommand":-1,"configSnippet":-1,"useCases":61,"updatedAt":62},"chromedevtools-chrome-devtools-mcp","chromedevtools\u002Fchrome-devtools-mcp","Chrome DevTools for coding agents","Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent (such as Antigravity, Claude, Cursor or Copilot) control and inspect a live Chrome browser. It acts as a Model-Context-Protocol (MCP) server, giving your AI coding assistant access to the full power of Chrome DevTools for reliable automation, in-depth debugging, and performance analysis. A CLI is also provided for use without MCP.\n\n- : Uses Chrome DevTools to record traces and extract actionable performance insights. - : Analyze network requests, take screenshots and check browser console messages (with source-mapped stack traces). - . Uses puppeteer to automate actions in Chrome and automatically wait for action results.\n\nchrome-devtools-mcp exposes content of the browser instance to the MCP clients allowing them to inspect, debug, and modify any data in the browser or DevTools. Avoid sharing sensitive or personal information that you don't want to share with MCP clients.","https:\u002F\u002Fgithub.com\u002Fchromedevtools\u002Fchrome-devtools-mcp","https:\u002F\u002Fgithub.com\u002Fchromedevtools\u002Fchrome-devtools-mcp\u002Farchive\u002FHEAD.zip","Apache-2.0",53548,6623,84,[20],[59],{"slug":20,"name":27,"summary":28,"count":25},[8,53],[],"2026-08-30T04:31:17.11693",{"slug":64,"name":65,"categorySlug":8,"summary":66,"description":66,"categoryName":10,"sourceUrl":67,"homepageUrl":-1,"downloadUrl":68,"cliCommand":-1,"primaryLanguage":-1,"license":13,"stars":69,"forks":70,"trendScore":16,"qualityScore":71,"supportedClients":72,"clients":75,"tags":83,"installCommand":-1,"configSnippet":-1,"useCases":84,"updatedAt":85},"sickn33-agentic-awesome-skills","sickn33\u002Fagentic-awesome-skills","Agentic Awesome Skills is a library of 2,689+ installable SKILL.md playbooks. AAS Core helps Codex or Claude search the complete local catalog, record the skills the agent chooses, and preview a plan...","https:\u002F\u002Fgithub.com\u002Fsickn33\u002Fagentic-awesome-skills","https:\u002F\u002Fgithub.com\u002Fsickn33\u002Fagentic-awesome-skills\u002Farchive\u002FHEAD.zip",47598,6942,83,[73,74,20],"cursor","cline",[76,79,82],{"slug":73,"name":77,"summary":78,"count":25},"Cursor","常与开发类 MCP Server 搭配使用的 AI 代码编辑器。",{"slug":74,"name":80,"summary":81,"count":25},"Cline","面向智能体编程工作流的客户端，常见 MCP 集成较多。",{"slug":20,"name":27,"summary":28,"count":25},[8,13],[],"2026-07-19T02:10:25.868557",{"slug":87,"name":88,"categorySlug":8,"summary":89,"description":90,"categoryName":10,"sourceUrl":91,"homepageUrl":-1,"downloadUrl":92,"cliCommand":-1,"primaryLanguage":-1,"license":53,"stars":93,"forks":94,"trendScore":16,"qualityScore":71,"supportedClients":95,"clients":96,"tags":100,"installCommand":-1,"configSnippet":-1,"useCases":101,"updatedAt":102},"headroomlabs-ai-headroom","headroomlabs-ai\u002Fheadroom","Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.","██╗ ██╗███████╗ █████╗ ██████╗ ██████╗ ██████╗ ██████╗ ███╗ ███╗ ██║ ██║██╔════╝██╔══██╗██╔══██╗██╔══██╗██╔═══██╗██╔═══██╗████╗ ████║ ███████║█████╗ ███████║██║ ██║██████╔╝██║ ██║██║ ██║██╔████╔██║ ██╔══██║██╔══╝ ██╔══██║██║ ██║██╔══██╗██║ ██║██║ ██║██║╚██╔╝██║ ██║ ██║███████╗██║ ██║██████╔╝██║ ██║╚██████╔╝╚██████╔╝██║ ╚═╝ ██║ ╚═╝ ╚═╝╚══════╝╚═╝ ╚═╝╚═════╝ ╚═╝ ╚═╝ ╚═════╝ ╚═════╝ ╚═╝ ╚═╝ The context compression layer for AI agents\n\n60–95% fewer tokens (for JSON data), 15-20% fewer tokens (for coding agents) · library · proxy · MCP · content-aware compressors · local-first · reversible\n\nDocs · Install · Proof · Agents · Discord · llms.txt\n\nAI agents \u002F LLMs: read \u002Fllms.txt here, or fetch the live index \u002F full docs blob .\n\nHeadroom compresses everything your AI agent reads — tool outputs, logs, RAG chunks, files, and conversation history — before it reaches the LLM. Same answers, fraction of the tokens.\n\nLive: 10,144 → 1,260 tokens — same FATAL found.","https:\u002F\u002Fgithub.com\u002Fheadroomlabs-ai\u002Fheadroom","https:\u002F\u002Fgithub.com\u002Fheadroomlabs-ai\u002Fheadroom\u002Farchive\u002FHEAD.zip",75370,5848,[73,74,20],[97,98,99],{"slug":73,"name":77,"summary":78,"count":25},{"slug":74,"name":80,"summary":81,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8,53],[],"2026-08-30T08:28:44.109415",5565,1,5]