Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
playwright_mcp
Agents & frameworksinvisible playwright mcp: Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use.
git clone https://github.com/oss-invisible/playwright_mcp.git -
skills
SkillsFirecrawl agent skills for Claude Code, Codex and Cursor: web search, scraping, crawling and browser interaction. Firecrawl is the most complete web data API for AI agents.
git clone https://github.com/firecrawl/skills.git -
kindly-web-search-mcp-server
MCP serversKindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, Hermes, etc.). Supports Serper, Tavily, and SearXNG.
git clone https://github.com/Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server.git -
Clouds-Coder
Agents & frameworksClouds Coder is a local-first coding agent platform centered on separating the CLI execution plane from the Web user plane, with Web UI, Skills Studio, resilient streaming, and long-task recovery controls.
git clone https://github.com/FonaTech/Clouds-Coder.git -
clay
Agents & frameworksA self-hosted workspace where people and coding agents work together across projects, sessions, and providers.
git clone https://github.com/chadbyte/clay.git -
google-maps-scraper
Skillsscrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
git clone https://github.com/gosom/google-maps-scraper.git -
WebsiteBench
Datasets & benchmarksCan AI agents rebuild websites through browser exploration?
git clone https://github.com/TIGER-AI-Lab/WebsiteBench.git -
portal-tunnel
SkillsPublishes localhost services to the agentic web through self-hostable, trustless relays.
git clone https://github.com/gosuda/portal-tunnel.git -
agentql-mcp
MCP serversModel Context Protocol server that integrates AgentQL's data extraction capabilities.
git clone https://github.com/tinyfish-io/agentql-mcp.git -
openserp
AI repositoriesSelf-hosted web search for AI agents and SEO. Google, Bing, Yandex, Baidu, DuckDuckGo & Ecosia, rendered in a real browser: ranked results and clean page Markdown. API, CLI, MCP 🎉
git clone https://github.com/karust/openserp.git -
agent-skills
SkillsYou.com skills and plugins for web search, content extraction, research, finance, and integration discovery, helping AI agents build with up-to-date web context.
git clone https://github.com/youdotcom-oss/agent-skills.git -
Mika
AI repositoriesAn on-device AI agent for Android that operates apps and the web to get things done for you.
git clone https://github.com/wangzan101/Mika.git -
agents-universe
Agents & frameworks不是问答机器人,而是能真正干活的数字分身。共享智能体,共享项目上下文,让项目所有成员一起协同工作。同时智能体会像人一样通过资料或者工作抽象和总结经验到项目上下文中
git clone https://github.com/agents-universe/agents-universe.git -
trustgraph
AI repositoriesThe open-source ontology runtime for AI agents.
git clone https://github.com/trustgraph-ai/trustgraph.git -
webclaw
MCP serversFast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.
git clone https://github.com/0xMassi/webclaw.git -
pi-research
SkillsWeb research for your agents with smart and safe tooling + knowledge store
git clone https://github.com/Lincoln504/pi-research.git -
opencraft
Agents & frameworksTypeScript agent workbench for Web, Electron and Expo with pluggable execution hosts and managed Web updates
git clone https://github.com/opencraft-app/opencraft.git -
oc
Agents & frameworksTurn any website into a compact CLI tailored for AI agents. Browse the web in hundreds of tokens, not tens of thousands.
git clone https://github.com/only-cli/oc.git -
CADAM
Agents & frameworksCADAM is the open source text-to-CAD web application
git clone https://github.com/Adam-CAD/CADAM.git -
ctf-super-hub
Skills面向小白用户的 CTF / 逆向 Skills 整合包:自动分流、头脑风暴、教学模式、比赛模式、只提示模式
git clone https://github.com/asdfgh1445/ctf-super-hub.git -
CloakBrowser
Agents & frameworksStealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 50+ tests passed.
git clone https://github.com/CloakHQ/CloakBrowser.git -
brightdata-mcp
MCP serversBright Data's Web MCP server enabling AI agents to search, extract & navigate the web
@brightdata/mcp@4.8.0 -
MiroFlow
Agents & frameworks🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI
git clone https://github.com/MiroMindAI/MiroFlow.git -
stealth-browser-mcp
MCP serversStealth browser automation for AI agents over MCP and the Chrome DevTools Protocol: navigation, network hooks, DOM extraction, and pixel-accurate UI cloning.
git clone https://github.com/vibheksoni/stealth-browser-mcp.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.