What it does
Core capabilities at a glance
- AI Agents
- AI Crawler
- AI Scraping
- AI Search
- Crawler
- Data Extraction
- Html TO Markdown
- Markdown
Deep dive
The full breakdown - performance, comparisons, and setup
firecrawl
firecrawl is an agent framework - The web data API to search, scrape, and interact at scale. 🔥.
Overview
The API to search, scrape, and interact with the web at scale. 🔥 The web data API to find sources, extract content, and turn it into clean Markdown or structured data your agents can ship with. Open source and available as a hosted service.
- Industry-leading reliability: Covers 96% of the web, including JS-heavy pages — no proxy headaches, just clean data (see benchmarks) - Blazingly fast: P95 latency of 3.4s across millions of pages, built for real-time agents and dynamic apps - LLM-ready output: Clean markdown, structured JSON, screenshots, and more — spend fewer tokens, build better AI apps - We handle the hard stuff: Rotating proxies, orchestration, rate limits, JS-blocked content, and more — zero configuration - Agent ready: Connect Firecrawl to any AI agent or MCP client with a single command - Media parsing: Parse and extract content from web-hosted PDFs, DOCX, and more - Actions: Click, scroll, write, wait, and press before extracting content - Open source: Developed transparently and collaboratively — join our community
Sign up at firecrawl.dev to get your API key. Try the playground to test it out.
Get LLM-ready data from any website — markdown, JSON, screenshots, and more.
Scrape a page, then interact with it using AI prompts or code.
firecrawl is open-source, written primarily in TypeScript, with 185,586 GitHub stars under the AGPL-3.0 license. The latest release is v2.11.0 (2026-06-19).
Key capabilities
From the project's documentation:
- Blazingly fast: P95 latency of 3.4s across millions of pages, built for real-time agents and dynamic apps
- LLM-ready output: Clean markdown, structured JSON, screenshots, and more — spend fewer tokens, build better AI apps
- Agent ready: Connect Firecrawl to any AI agent or MCP client with a single command
- Media parsing: Parse and extract content from web-hosted PDFs, DOCX, and more
- Actions: Click, scroll, write, wait, and press before extracting content
- Open source: Developed transparently and collaboratively — join our community
How it fits a local-AI stack
firecrawl runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:
Sources
- Source code & docs: firecrawl/firecrawl
- Official website: https://firecrawl.dev
Stats from GitHub, 2026-09-28.
Frequently asked
Quick answers to common questions
What is firecrawl?
firecrawl is a agent-framework tool for local AI workloads. The web data API to search, scrape, and interact at scale. 🔥
Is firecrawl free and open source?
Yes, firecrawl has 185,586 GitHub stars and is licensed under AGPL-3.0. You can self-host it for free on web.
What platforms does firecrawl support?
firecrawl runs on web.
What hardware do I need for firecrawl?
The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. firecrawl has 185,586 GitHub stars and an active community.
Does firecrawl support GPU acceleration?
firecrawl's GPU support depends on your specific setup. Check the documentation for details. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.
What are the best alternatives to firecrawl?
Popular alternatives include other agent-framework tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.
How much does firecrawl cost?
firecrawl is free-open-source. It is completely free and open source to self-host.
Pairs well with
Complementary tools, models, and hardware