Open-source webclaw: Rust-based local-first web extraction tool with CLI, API, and MCP server
tom_doerr · x · 2026-08-10
webclaw is an open-source project that converts websites into clean Markdown, JSON, and LLM-ready context for AI agents and RAG pipelines. It offers a CLI, REST API, and MCP server, along with SDKs. Built in Rust, it emphasizes local-first and fast extraction, enabling scraping, crawling, and structured data extraction. The GitHub repo has 2.1k stars and 213 forks, with 291 commits, Docker deployment, and a Chinese README.
More from coding & agent
- Shift in AI Coding Workflows: Embracing Long Context Over New Threads — JeremyNguyenPhD · 2026-08-10
- Rust and WASM Optimizations Deliver Massive Speedups for AI Projects — doodlestein · 2026-08-10
- Meta Releases Muse Glimmer: 30B Open-Weights Model for Local Agent Workflows — rohanpaul_ai · 2026-08-10
- Disentangling AI Agent Authorization: Access Control vs Data Binding — Prestigious-Run-1954 · 2026-08-10
- Proposal: Every Company Needs a Background AI Agent to Act as 'Cassandra' — threepointone · 2026-08-10
- Claude Desktop Reported Missing Latest MCP Protocol Support — Otherwise-Rip-9842 · 2026-08-10