Vibe Coding Discoverservo-fetch
View on GitHubA self-contained browser engine that fetches, renders, and extracts web content as Markdown, JSON, or screenshots — no Chromium, no API key, no setup.
Rust browser engine built on embedded Servo that renders pages and extracts Markdown, schema-driven JSON, or PNG screenshots with no Chromium or API key. Ships as CLI, Rust/Python/Node libraries, HTTP API, built-in MCP server, and agent skill for feeding agents web content.
Use Cases
Feed clean Markdown of web pages to LLM agentsScrape sites into structured JSON via CSS-selector schemaCapture PNG or full-page screenshots without a GPU or ChromiumExpose web fetch/crawl/screenshot as MCP tools to agentsCrawl documentation sites for RAG ingestionDiscover URLs quickly via sitemaps without renderingRun JavaScript in a page and extract resultsBatch fetch many URLs in parallelServe web extraction over a REST HTTP API in DockerExtract accessibility tree with roles and bounding boxesReplace Playwright in agent stacks with a single binaryParse PDFs fetched over the web
Built With
- Language
- Rust
- Frameworks
- Servo · SpiderMonkey · rmcp · Axum · Tokio · reqwest · clap · serde · tower · Strands Agents
Tags
web-scraping · headless-browser · markdown-extraction · mcp-server · agent-skills · rust · cli · screenshots · crawling · sitemap · javascript-execution · accessibility-tree · json-extraction · browser-engine · http-api · python-node-sdk