Firecrawl review

Q: How do I install Firecrawl?

Run pip install firecrawl. It needs Node.js >=18.0.0. The install section above has the other options from the project's README.

Firecrawl is an API and open source project to search, scrape, crawl, and interact with web pages, returning LLM-ready markdown or JSON for AI agents.

Updated Nov 1, 2026. Review written Oct 22, 2026 from the project's own sources; usage data refreshed every Monday.

TL;DR

Firecrawl is a web data API for AI agents that turns URLs, search results, and documents into clean markdown, structured JSON, or screenshots. Firecrawl is for developers building AI apps and agents that need live web content. Firecrawl is open source, available as a hosted service, and connects to agents through SDKs, a CLI, skills, and an MCP server.

197.4kGitHub stars
+2.6knew stars, week of Oct 25
~2.9Mdownloads a week, +3% vs 4-week avg
#6in RAG, data and memory this week

Firecrawl at a glance

Category: RAG, data and memory
Maintained by: Firecrawl (organization, @firecrawl on GitHub)
License: AGPL 3.0
Language: TypeScript, Python, Rust
Repository: github.com/firecrawl/firecrawl
Website: firecrawl.dev
npm package: @mendable/firecrawl-js 4.50.1
PyPI package: firecrawl-py 4.53.2
Latest release: @mendable/firecrawl-js 4.50.1 on npm, Oct 21, 2026
First published: Apr 15, 2024

What Firecrawl does

Firecrawl converts any URL to markdown, HTML, screenshots, or structured JSON through its Scrape endpoint.
Firecrawl searches the web and returns full page content from the results.
Firecrawl crawls all URLs of a website in one request, and its Map endpoint discovers a site's URLs.
Firecrawl's Interact endpoint lets you click, fill forms, and navigate a scraped page using natural-language prompts or Playwright code.
Firecrawl's Agent endpoint gathers data from a plain description, without needing URLs upfront, and can return output matching a schema.
Firecrawl parses uploaded files such as PDF, DOCX, XLSX, and HTML up to 50 MB into Markdown, JSON, or a summary.
Firecrawl can notify you when content on a website changes through its Monitor feature.

How it works

Firecrawl runs as a hosted API at api.firecrawl.dev, called with an API key over REST, the CLI, or SDKs for Python, Node.js, Go, and other languages. The SDKs handle polling for async jobs like crawls. AI agents connect through the firecrawl-mcp server or an installed skill that works with Claude Code, OpenCode, and others. The project is also open source.

How to install and start using Firecrawl

With pip

pip install firecrawl

With npm

npm install firecrawl

As an agent skill

npx -y firecrawl-cli@latest init --all --browser

Requirements

A Firecrawl API key from firecrawl.dev for most API use.
Node.js 18 or later for the JavaScript SDK.
Python 3.8 or later for the Python SDK.

First steps

Sign up at firecrawl.dev to get an API key, or test requests in the playground first.
Install the Python or Node.js SDK and create a Firecrawl client with your API key.
Call scrape on a URL with formats set to markdown to get LLM-ready page content.
To use Firecrawl from an agent, add the firecrawl-mcp server to your MCP client config with FIRECRAWL_API_KEY set.

Who Firecrawl is for

Developers building AI agents that need current web content as markdown or structured JSON.
Teams connecting coding agents like Claude Code or OpenCode to web search and scraping through MCP or skills.
Pipelines that turn PDFs, DOCX, and other documents into clean Markdown for LLMs.
Automating multi-step page interactions, such as searching a site and clicking results, before extracting data.

Limitations to know

Firecrawl's quick start and hosted endpoints require an API key; keyless access covers only some core endpoints from official clients.
Firecrawl usage is metered in credits, which crawl jobs report as consumed.
Firecrawl's Zero Data Retention support for parsing and search is limited to enterprise plans or customers.
Firecrawl's /parse endpoint accepts files up to 50 MB.

Is Firecrawl growing? Usage data

In the week of Oct 25–31, 2026, Firecrawl ranked #91 on the Devtoolwatch Board and #6 in RAG, data and memory, with a momentum score of 65 out of 100. Its main package had about 2.9M downloads that week, +3% against its own 4-week average.

New GitHub stars per week for the last 12 weeks, from GitHub's stargazer history (today's stargazers by the week they starred).

Show the weekly numbers

New GitHub stars per week for Firecrawl
Week of	New stars
Aug 9, 2026	4.4k
Aug 16, 2026	3.3k
Aug 23, 2026	3.2k
Aug 30, 2026	2.9k
Sep 6, 2026	2.8k
Sep 13, 2026	2.8k
Sep 20, 2026	3k
Sep 27, 2026	3.3k
Oct 4, 2026	2.3k
Oct 11, 2026	2.5k
Oct 18, 2026	2.7k
Oct 25, 2026	2.6k

On Hacker News

How to Build an AI Software Factory: Agents That Open, Review, and Merge PRs, 31 points and 14 comments (Sep 11, 2026)
Show HN: Llms.txt Generator – Turn websites into a text file to feed to any LLM, 28 points and 6 comments (Nov 21, 2024)
Show HN: API to turn entire websites into Markdown, 23 points and 4 comments (Apr 16, 2024)
Turn entire websites into LLM-ready data, 16 points and 11 comments (Apr 13, 2024)
Show HN: From SERP to LLM-Ready Data Markdown in Seconds with Firesearch, 14 points and 0 comments (Apr 25, 2024)

The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.

Firecrawl alternatives

Other RAG, data and memory tools on the Board in the week of Oct 25–31, 2026, by momentum:

RAG, data and memory ranked by momentum, the week of Oct 25–31, 2026
Rank	Tool	Stars	Downloads/wk
#1	XERJXERJ is a local-first search engine and MCP server for AI agents, packaged as one Rust binary with an Elasticsearch-compatible API.	17.9k	–
#2	MemvidMemvid is a single-file memory layer for AI agents that packages data, embeddings, search indexes, and metadata into one portable .mv2 file.	17.3k	–
#3	LEANNLEANN is a Python vector database and RAG library that recomputes embeddings on demand to keep indexes small on personal devices.	13.7k	–
#4	GraphifyGraphify is an AI coding assistant skill that turns a codebase, with its docs, PDFs, images and videos, into a queryable knowledge graph.	140k	480.7k
#5	MarkItDownMarkItDown is a lightweight Python utility from Microsoft that converts PDFs, Office documents, images, audio and other files to…	193.2k	4.7M
#7	Mem0Mem0 is a memory layer for AI agents and apps that stores and retrieves user, session, and agent context across interactions.	68.2k	884.1k

All RAG, data and memory tools, ranked

Recent Firecrawl releases

v2.11.0, Jun 19, 2026
v2.10, May 15, 2026
v2.9.0, Apr 10, 2026
v2.8.0, Feb 3, 2026
v2.7.0, Dec 5, 2025

Firecrawl FAQ

Is Firecrawl free and open source?

Yes. Firecrawl's source code is on GitHub (firecrawl/firecrawl) under the AGPL 3.0 license, so you can use it for free. Its website also links to a pricing page (https://firecrawl.dev/pricing) for any paid plans.

How do I install Firecrawl?

Run pip install firecrawl. It needs Node.js >=18.0.0. The install section above has the other options from the project's README.

Is Firecrawl still maintained?

Yes. The firecrawl/firecrawl repository was last updated on Oct 22, 2026, and the latest release, @mendable/firecrawl-js 4.50.1 on npm, came out on Oct 21, 2026.

How popular is Firecrawl?

Firecrawl has 197.4k GitHub stars as of Nov 1, 2026. It gained 2.6k new stars in the week of Oct 25–31, 2026, against a 12-week average of 3k a week. Its main package had about 2.9M downloads that week, +3% against its own 4-week average. That made it #6 among RAG, data and memory tools on the Devtoolwatch Board.

Firecrawl vs Exa: how do they compare?

Firecrawl and Exa are both tracked by Devtoolwatch as RAG, data and memory tools. Firecrawl has 197.4k GitHub stars and Exa has 237. In the week of Oct 25–31, 2026, Firecrawl's main package had 2.9M downloads and Exa's had 1.2M. Exa Python SDK is the official Python package for Exa, the web search API for AI, covering search, page contents, answers and agents. Exa review.

Firecrawl vs Crawl4AI: how do they compare?

Firecrawl and Crawl4AI are both tracked by Devtoolwatch as RAG, data and memory tools. Firecrawl has 197.4k GitHub stars and Crawl4AI has 86.7k. In the week of Oct 25–31, 2026, Firecrawl's main package had 2.9M downloads and Crawl4AI's had 358.1k. Crawl4AI is an open-source Python web crawler and scraper that turns websites into clean, LLM-ready Markdown or structured JSON for RAG and agents. Crawl4AI review.

What are the best alternatives to Firecrawl?

Other RAG, data and memory tools on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: XERJ (#1), Memvid (#2), LEANN (#3), Graphify (#4), MarkItDown (#5). The alternatives table above has their numbers.

How do I use Firecrawl with Claude Code?

Firecrawl connects to Claude Code by installing its skill with npx -y firecrawl-cli@latest init --all --browser, then restarting the agent. You can also add the firecrawl-mcp server to your MCP configuration with your API key.

How do I use the Firecrawl MCP server?

Firecrawl's MCP server is added to an MCP client's config under mcpServers, running npx with args -y and firecrawl-mcp, and setting FIRECRAWL_API_KEY in env. Any MCP-compatible client can use it.

Can I use Firecrawl without an API key?

Firecrawl offers keyless access to /scrape, /search, /interact, and /parse from official clients such as MCP and the CLI, starting in v2.11.0. Other endpoints and the quick start use an API key from firecrawl.dev.

How do I use the Firecrawl API?

Firecrawl's API takes POST requests to endpoints like https://api.firecrawl.dev/v2/scrape with a Bearer API key and a JSON body. Crawl requests return a job ID you poll for status. The SDKs handle polling automatically.

Can Firecrawl handle JavaScript-heavy pages?

Firecrawl handles JS-heavy pages, rotating proxies, rate limits, and JS-blocked content without configuration. It can also run actions like click, scroll, write, wait, and press before extracting content.

Sources

Firecrawl README badge

Maintainers can show the tool's weekly Board rank in their README:

[![Devtoolwatch](https://index.devtoolwatch.com/badge/firecrawl.svg)](https://index.devtoolwatch.com/tools/firecrawl/)

How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].