Context management
Firecrawl
Web crawl and scrape API producing clean markdown pages for agent context windows
★ 200,338 on GitHub · last commit Nov 10, 2026
What it is
Firecrawl solves the ugly half of live-web context: turning rendered pages into clean markdown that fits a token budget, and its pricing page ships a dedicated agent onboarding path for LLM callers. The AGPL-3.0 core plus a paid hosted tier is a textbook open-core commercial shape.
At a glance
- Business model
- Open source + paid cloud
- Pricing
- Free $0 (500 searches or 1,000 pages, 2 concurrent); Hobby $16/mo; Standard $83/mo; Growth $333/mo; Scale $599/mo; enterprise custom pricing page ↗
- License
- AGPL-3.0
- Self-hosting
- Yes, can be self-hosted
- Access
- REST API and SDKs; search, scrape and crawl endpoints; agent onboarding docs
GitHub activity
This product has a public repository, so we read it nightly from the GitHub API. Stars measure developer attention, not quality or market share.
“Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥” (repository description)
- Stars
- 200,338
- Forks
- 10,540
- Open issues
- 782
- Last commit
- Nov 10, 2026
- License (GitHub)
- AGPL-3.0
Links and sources
- Official sitewww.firecrawl.dev/pricing
- Pricingwww.firecrawl.dev/pricing
- GitHub repositorygithub.com/firecrawl/firecrawl
Facts verified nov 10, 2026; added nov 10, 2026. Vendor facts come from the vendor’s own pages; benchmark claims are self-reported unless we say otherwise.