Webclaw is a web scraping API for LLMs and AI agents. It turns websites into markdown, JSON, or structured data from a URL, with a stated focus on clean output and fewer tokens than raw HTML. The page also describes it as a drop-in Firecrawl replacement and says it works without a headless browser.
Its listed surfaces include a cloud API with REST endpoints for scrape, crawl, and search, plus an MCP Server and a CLI tool. Webclaw says the same engine drives the API, CLI, and MCP server, and its features page mentions that every endpoint has its own page. The product text also says it handles bot protection and returns static pages in around 118 ms.
The service is described for use cases including RAG, agents, research, and monitoring. It is mentioned alongside integrations with LangChain, Cursor, and n8n, and it says it can be plugged into Claude, Cursor, and agents through the MCP Server. The site also advertises live scraping with no signup and three free runs a day.
Pricing-related text on the page includes free credits for open-source builders, a free trial prompt, and a statement to save 20% on any yearly plan.
In the API design, testing & docs space, webclaw takes a focused approach. It focuses on extracting structured data from websites for use in LLMs and AI agents without browser automation. webclaw is a B2B product aimed at developers building AI agents, LLM applications, and data extraction workflows. webclaw follows a freemium model. It ships for the command line and API.
Behind webclaw is 0xMassi, and it first shipped in 2026. The project is developed in the open on GitHub with 1.7k stars and 150 commits in the last 90 days. Key capabilities include REST API endpoints, CLI tool, and structured data extraction. It exposes integrations via an MCP server and a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do