On November 18 Firecrawl announced Firecrawl Local on its official X account: scraping, crawling and site mapping rebuilt as a single Rust binary that runs on your own machine. It is open source in apps/local of the firecrawl/firecrawl repository (AGPL-3.0) and installs with cargo install firecrawl-local. It turns pages into clean markdown, plugs into Claude Code, Cursor, Codex, Gemini CLI and other tools as an MCP server, and serves the Firecrawl v2 API on localhost:3002, so existing SDK code works by changing the API URL. The official post claims scraping is 37x faster than the self-hosted version with 230x less memory (11 MB idle).
Key Takeaways
- ✓One binary: no database, queue or container; install with cargo install firecrawl-local (needs Rust and a C compiler)
- ✓firecrawl-local init adds the MCP server to Claude Code, Claude Desktop, Cursor, Windsurf, Gemini CLI and Codex, backing up each config first
- ✓serve exposes the v2 scrape, map, crawl and batch scrape routes on 127.0.0.1:3002, with no API key needed for local routes
- ✓Search, pages that block your machine and Alexandria data providers still go to Firecrawl Cloud; FIRECRAWL_CLOUD=off keeps everything local
- ✓The speed figures (37x faster than self-hosted, 230x less memory) come from the official post; the docs do not describe how they were measured
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background
More and more AI agents need to read web pages, but letting an agent scrape usually means calling a paid cloud API or self-hosting a full Firecrawl server with queues and workers, which is heavy for individual developers and local agents.
How it works
According to the official docs, Firecrawl Local is a Rust binary that fetches and cleans pages on your machine with the same cleaning code the Firecrawl API uses, rendering JavaScript-heavy pages in the Chrome already installed locally. It runs as a stdio MCP server or serves the v2 API on localhost. Crawl and batch jobs live in memory and expire after an hour.
Benchmarks
The official X post claims scraping is 37x faster than the self-hosted version with 230x less memory (11 MB idle). The docs do not describe the test method, and there is no third-party evaluation yet.
What it means for developers
After cargo install firecrawl-local, run firecrawl-local init to wire it into common AI coding tools, then restart them. If your agent browses untrusted sites, the docs recommend registering it as firecrawl-local mcp --public-only so hidden instructions in a page cannot steer it into internal addresses.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.