selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

firecrawl logo

Self-host firecrawl

v2.11.0

API for AI agents to search, scrape, and interact

ReleaseOpen SourceAGPL-3.0
Updated4 months ago
LanguageTypescript
Setup difficultyAdvanced
Stars
201 884
Rating
5.0 (1)
Port
3002 (Firecrawl API)
Requires
PostgreSQL
Docker
ghcr.io/firecrawl/firecrawl
Install with Docker Compose
firecrawl screenshot 1

What is firecrawl?

Firecrawl is a web data platform built for AI agents that need to find, read, and act on live web content. It provides three core capabilities: Search (find relevant pages and get full content in one call), Scrape (convert any URL to markdown, HTML, screenshots, or structured JSON with automatic JavaScript rendering), and Interact (click, scroll, type, and navigate pages before extracting data). Additional endpoints include Crawl (scrape entire websites), Map (discover all URLs instantly), Batch Scrape (process thousands of URLs asynchronously), and Agent (autonomous multi-step research). The self-hosted version runs via Docker Compose with PostgreSQL, Redis, RabbitMQ, and a Playwright service, exposing the API on port 3002. The open-source edition (AGPL-3.0) includes core scraping, crawling, and search; advanced features like Agent, Browser, Interact, and managed anti-bot infrastructure are Cloud-only. Firecrawl offers official SDKs for Python, Node.js, Go, Rust, Java, Elixir, Ruby, .NET, and PHP, plus a CLI and MCP server for AI agent integration.

firecrawl alternatives

All self-hosted alternatives to Apify →

Should you self-host firecrawl?

firecrawl scores 91/100 on selfhost.directory (how scoring works) and ranks #1 of 16 in Web Scraping. It has 201 884 GitHub stars, +11 331 in the last 30 days.

It shipped 9 stable releases in the past year. The latest, apps/go-sdk/v1.15.0, came out on 8 September 2026. New versions land roughly every 9 days.

Setup is advanced: plan for several services and some ongoing maintenance. An official Docker image is available. It is AGPL-3.0-licensed and written mostly in Typescript.

Its closest alternative on selfhost.directory is webclaw (64/100, 2 443 stars). firecrawl scores higher overall. See firecrawl vs webclaw side by side.

Features

  • CLI
  • JavaScript Rendering
  • Media Parsing
  • Token-efficient Output

firecrawl README


🔥 Firecrawl

The API to search, scrape, and interact with the web at scale. Firecrawl is the context API for AI agents. 🔥 Open source and available as a hosted service.

Pst. Hey, you, join our stargazers :)

How to install firecrawl

Install firecrawl with Docker Compose

Environment variables
USE_DB_AUTHENTICATION, POSTGRES_USER, POSTGRES_PASSWORD, POSTGRES_DB, REDIS_URL, OPENAI_API_KEY, OLLAMA_BASE_URL, PROXY_SERVER, BULL_AUTH_KEY, NUQ_BACKEND

git clone https://github.com/firecrawl/firecrawl.git cd firecrawl git checkout v2.11.162 cat > .env <<'EOF' USE_DB_AUTHENTICATION=false POSTGRES_USER=postgres POSTGRES_PASSWORD=replace-with-at-least-32-random-characters POSTGRES_DB=postgres EOF docker compose up --build -d

Pinned to release v2.11.162; authentication disabled for evaluation; requires Git, Docker Engine, Docker Compose v2, curl

How to configure firecrawl

  • PORT3002API external port
  • HOST0.0.0.0API host bind address
  • USE_DB_AUTHENTICATIONfalseEnable database-backed authentication (requires complete identity setup)

    values: true|false

  • OPENAI_API_KEYOpenAI API key for LLM-backed features
  • OLLAMA_BASE_URLOllama base URL for local LLM

firecrawl releases & version history

@ Every self-hosted release, weekly

One Monday email with the week's stable releases across the directory.

More in Web Scraping

Rate this project

Click to rate — no account needed.

0 comments

Posting as guest
Loading comments…