Firecrawl
API that turns websites into clean Markdown or structured data for LLMs.
Quick answer
Firecrawl is an API that turns websites into clean Markdown or structured data for LLMs, listed under Web scraping for AI. A typical small-business use: feed your own website, help center or a supplier catalogue into a RAG knowledge base. The project publishes no official RAM figure, so we do not estimate a monthly server cost. License: AGPL-3.0 (SDKs and some UI components MIT), which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 22, 2026.
What is Firecrawl?
Firecrawl scrapes single pages, crawls whole sites, maps URLs and runs web searches, and returns the content as Markdown, HTML or JSON that RAG pipelines and agents can use directly. The self-hosted stack runs with Docker Compose and includes a Playwright browser; LLM-based extraction needs an OpenAI-compatible provider or Ollama.
Where it fits in a 10–200 person business
- Feed your own website, help center or a supplier catalogue into a RAG knowledge base
- Let an internal agent or n8n workflow read web pages as clean text
- Monitor competitor or partner pages by crawling them on a schedule
These use cases are our editorial suggestions, not claims made by the project.
Can a business use Firecrawl? (license)
| License | AGPL-3.0 (SDKs and some UI components MIT) |
|---|---|
| Type | Network copyleft (AGPL): Like GPL, and also applies when users access a modified version over a network. |
| Internal business use | Allowed under the license text |
| What to watch | Free for internal and commercial use. If you modify Firecrawl and let users interact with it over a network, you must offer them the modified source under AGPL-3.0. The SDKs are MIT. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
Data & compliance: does Firecrawl phone home?
| Telemetry (usage data sent to the vendor) | Off by default (opt-in) PostHog events are sent only if you set POSTHOG_API_KEY (empty in the example .env). Source: github.com/firecrawl/firecrawl/blob/main/apps/api/.env.example |
|---|---|
| Other calls home by default (updates, marketplaces, default cloud services) | Not documented |
| Single sign-on (OIDC / SAML / LDAP) | Not documented |
| Audit log | Not documented |
| Role-based access control (RBAC) | Not documented |
| Data residency / GDPR notes from the project | Not documented |
Checked against the project's own docs and repository on . "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.
What hardware does Firecrawl need?
The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.
Firecrawl does not publish a verified minimum host size; the stack runs several services (API, workers, Playwright, Redis, RabbitMQ, PostgreSQL).
How much does it cost to host Firecrawl per month?
The project publishes no RAM figure we could verify, so we do not estimate a cost.
How to deploy Firecrawl
Method: Docker Compose (build from source)
git clone https://github.com/firecrawl/firecrawl.git
cd firecrawl
git checkout v2.11.162 # the release the official guide was verified against
cat > .env <<'ENV'
USE_DB_AUTHENTICATION=false
POSTGRES_USER=postgres
POSTGRES_PASSWORD=replace-with-at-least-32-random-characters
POSTGRES_DB=postgres
ENV
docker compose up --build -d
# API on http://localhost:3002From the official instructions: docs.firecrawl.dev/contributing/self-host. Always check the source for the current version before you run it.
Known gotchas when self-hosting Firecrawl
- The default self-hosted API has no authentication. Keep it on a trusted network, or add a full auth design, TLS and network policy before exposing it. source
- Screenshots and page actions are not available in the default stack; they need the separate Fire-engine service. Agent, browser and some special formats are cloud-only or need extra services. source
- The root Compose file defines no persistent volumes for PostgreSQL, Redis and RabbitMQ. Add volumes and backups before relying on the data. source
Firecrawl FAQ
How much RAM does Firecrawl need?
Firecrawl does not publish an official RAM figure, so we do not state one. Firecrawl does not publish a verified minimum host size; the stack runs several services (API, workers, Playwright, Redis, RabbitMQ, PostgreSQL).
How much does it cost to self-host Firecrawl?
The software is free to download. The project publishes no official RAM figure, so we do not estimate a monthly server cost.
Is Firecrawl free for commercial use?
Firecrawl is licensed under AGPL-3.0 (SDKs and some UI components MIT) (Network copyleft (AGPL)). Internal business use is allowed under the license text. Free for internal and commercial use. If you modify Firecrawl and let users interact with it over a network, you must offer them the modified source under AGPL-3.0. The SDKs are MIT. This is a summary, not legal advice.
What are common problems when self-hosting Firecrawl?
The default self-hosted API has no authentication. Keep it on a trusted network, or add a full auth design, TLS and network policy before exposing it. Screenshots and page actions are not available in the default stack; they need the separate Fire-engine service. Agent, browser and some special formats are cloud-only or need extra services. The root Compose file defines no persistent volumes for PostgreSQL, Redis and RabbitMQ. Add volumes and backups before relying on the data.
Is Firecrawl still maintained?
Yes, it is actively developed. Last commit: Oct 22, 2026. Latest release: v2.11.0 (Jun 19, 2026). Checked Oct 22, 2026.
How do I install Firecrawl?
The official method is Docker Compose (build from source). The exact commands are in the "How to deploy" section above and in the official instructions: https://docs.firecrawl.dev/contributing/self-host
Sources
- GitHub repository: github.com/firecrawl/firecrawl
- Official documentation, Hardware requirements, Deploy instructions, Gotcha 1, Gotcha 2: docs.firecrawl.dev/contributing/self-host
- License text: github.com/firecrawl/firecrawl/blob/main/LICENSE
- Gotcha 3: github.com/firecrawl/firecrawl/blob/main/SELF_HOST.md
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-22. Spotted something out of date? Tell us.