Submit a resource

Navigation

Back to directory

webclaw

A Rust-based, local-first web content extraction tool that turns a URL into clean Markdown, JSON or other LLM-ready output for AI agents and RAG pipelines, available as a CLI, an MCP server, a REST API and a self-hostable server.

Visit website (opens in a new tab)webclaw.io
webclaw

webclaw turns a web page into clean, structured content that a language model or agent can use directly, instead of a blocked page, a login wall, or raw HTML full of navigation, scripts and ads. It scrapes single pages, crawls a site, and extracts structured data, running natively in Rust.

This repository contains the open-source CLI, MCP server, extraction engine and self-hostable server behind webclaw.io, a separate hosted extraction API. It can be used from a terminal, wired into Claude, Cursor and other MCP-compatible clients, called as a hosted API from an application, or self-hosted as an open-source server.

It installs through an automatic MCP setup script that detects and configures supported agent clients, through Homebrew, or from prebuilt binaries for macOS, Linux and Windows.

More in Browser automation

See all 88

  • browser-session-ctl

    github.com

    Loads an unpacked Chrome extension that lets a local AI coding agent click, type and read the tabs, cookies and logins of a Chrome window you already have open.

  • Hronaut

    hronaut.dev

    A visible, persistent Electron browser that exposes durable, named agent workspaces over MCP, so a coding agent's browser session stays open and inspectable independently of any one AI conversation.

  • Prompt OS

    github.com

    A desktop AI agent for Windows that executes terminal commands, manages files, writes and runs code, browses the web and reads the screen, acting on natural-language requests rather than only answering them.

Cookies

We use necessary cookies to run the site. Measurement and marketing are optional; neither is used today. Privacy policy