Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.
webclaw is a web-content extraction tool that turns webpages into clean Markdown, JSON, and context suitable for language models. It is for AI agents and retrieval-augmented applications that need usable content from websites, and can be used through a CLI, REST API, SDKs, or MCP server. The catalogue includes instructions and an MCP integration for connecting compatible agents to it.
This repository also configures its own agents. See what webclaw tells them →