crw
Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use managed cloud.
- stars
- 1,048
- 30-day movement
- +217/day
- Related entries
- 75
- Connections
- 5
crw is a Rust web scraper, crawler, and search API that exposes a Firecrawl-compatible endpoint set (/scrape, /crawl, /search) plus an MCP server for AI agents. It ships as a single lightweight binary (claimed 6 MB RAM) and can be self-hosted or used via managed cloud.
Reach for it when you want Firecrawl/Tavily-style scraping and search endpoints with lower resource use and self-hosting under your control.
Use it to
- Self-host a Firecrawl-compatible scraping API
- Expose web scraping to AI agents via MCP
- Crawl sites and convert HTML to markdown
- Run a lightweight web search API endpoint
For Developers building AI agents needing self-hosted web scraping
- Role
- mcp-server
- Language
- Rust
- Licence
- AGPL-3.0
- Forks
- 81
- Open issues
- 1
- Last push
- 2026-09-17
- Latest release
- v0.0.4 · 2026-03-11
- Skills shipped
- 13