# Firecrawl

The context API to search, scrape, and interact with the web at scale. 🔥

Repository: https://github.com/firecrawl/firecrawl
Canonical: https://ross.abutalabs.com/products/firecrawl
Homepage: https://firecrawl.dev
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Topics: ai, crawler, markdown, scraper, html-to-markdown, llm, scraping, web-crawler, ai-scraping, webscraping, web-scraping, web-data, web-data-extraction, ai-agents, data-extraction, ai-crawler, ai-search, web-scraper, web-search
Last push: 2026-08-26T23:56:52+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 89, longevity 62
- inputs: {"age_days": 870, "days_push": 7, "days_rel": 75, "gap_med": 11.0, "n_releases_24m": 35}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 172809, forks 9538 (observed 2026-08-28T04:12:24.433781+00:00)

## What it is
Firecrawl is an open-source web scraping and crawling API that turns websites into clean Markdown, structured JSON, screenshots, and other LLM-ready formats. It handles JavaScript rendering, proxies, and rate limits, and is available both self-hosted and as a hosted service with an MCP server for AI agents.

## Use cases
- scrape websites into markdown for llm training
- crawl an entire site and extract structured data
- feed fresh web content into a rag pipeline
- extract data from js-heavy single page apps
- convert web-hosted pdfs and docx files to text
- give my ai agent the ability to search and read the web
- scrape pages that require clicking or scrolling before extraction

## When to choose
- you need reliable large-scale scraping without managing proxies or headless browsers
- you want clean markdown or structured output for LLMs and agents
- you need an MCP-ready web tool for AI agents
- you want both a hosted API and a self-hostable option

## When to avoid
- you only need simple static HTML fetching with no JS rendering
- you need a fully free solution at high volume without self-hosting
- your target sites require heavy authenticated session workflows beyond Firecrawl's actions

## Facets
- artifact type: service
- maturity: active
- function: web-scraping, search-engine, parser, rag, mcp, sdk
- domain: crawlers, artificial-intelligence, large-language-models, developer-tools
- platform: python, self-hosted, cloud
- tags: html-to-markdown, data-extraction, llm-ready-output, crawler, hosted-api, agentic-search, ai-agents, nodejs, web-server

## Member repositories
- firecrawl/firecrawl (main) score 88
- firecrawl/firecrawl-mcp-server (plugin) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:24.433781+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:10:50.174726+00:00, confidence not recorded.
  - readme: https://github.com/firecrawl/firecrawl (fetched 2026-08-28T04:12:24.433781+00:00, sha 1d4d3334ef0f)
- Data as of 2026-08-30T08:39:29.467469+00:00.