Get Started
Launch Week III (New)
Check out what’s new coming to Firecrawl in Launch Week III (April 14 - 20th)
Day 7 – Integration Day
Overview
For the final day of Launch Week III, we’re rolling out new and updated integrations that make it easier to connect Firecrawl to the tools and platforms you already use. From automation platforms to AI pipelines, Firecrawl now integrates with 20+ services, giving you a faster path from web data to workflow execution.Key Integration Updates
- Discord Bot: Trigger scrapes and receive structured results right inside your server. Learn more
- Make Integration: Visually build workflows powered by Firecrawl’s scraping and extraction. Learn more
- n8n Integration: Connect Firecrawl to custom automation flows. Learn more
- Langflow: Seamlessly embed Firecrawl agents into Langflow pipelines. Learn more
- LlamaIndex: Use Firecrawl with LlamaIndex to enrich and retrieve data intelligently. Learn more
- Dify: Integrate Firecrawl with Dify to automate AI workflows. Learn more
Day 6 – Firecrawl MCP
Overview
Today we’re launching a major upgrade to our Firecrawl MCP server, our implementation of the Model Context Protocol for LLM-connected scraping workflows. This release brings FIRE-1 agent support to the MCP, letting you unlock data hidden behind interaction barriers like logins and buttons — all via scrape and extract endpoints. We’re also introducing Server-Sent Events (SSE) support for local use, making setup and real-time integration easier than ever. These updates make it simpler to stream web data into LLM pipelines, with intelligent agents handling the heavy lifting.Key Features
- FIRE-1 Support: Use the web action agent via MCP’s scrape and extract endpoints.
- Interaction-Aware: Automatically navigates complex web barriers.
- SSE Support: Stream output in real time — locally or from our hosted MCP server.
- Plug-and-Play: Minimal setup needed for integration with your stack.
Day 5 – Developer Day
Overview
Today is all about developers. We’re rolling out upgrades that make building with Firecrawl smoother and more scalable — whether you’re working in Python, Rust, or your favorite editor. We’ve introduced a fully async Python SDK with named params and return types, powerful new features in the Rust SDK, expanded team support on every plan, and a brand new Firecrawl Dark Theme for VSCode and compatible editors.
Key Features
- Major Python SDK Improvements: Named params, return types, and Async added to our Python SDK
- Rust SDK Upgrades: Batch scraping, job cancellation, llms.txt generation, smarter search.
- Firecrawl Dark Theme: A sleek new theme for VSCode, Cursor, and Windsurf. Download it here.
- QoL Improvements: Plenty of small but meaningful changes to improve dev experience like no more team caps. All plans now include up to 20 seats.
Day 4 – LLMstxt.new
Overview
Today we’re announcing http://llmstxt.new — the fastest way to turn any website into a clean, consolidated text file for LLMs. Just addllmstxt.new/ in front of any URL, and you’ll get back a plain .txt file, optimized for AI training and inference. No boilerplate, no noise — just useful content.
Built on top of Firecrawl, this tool makes it effortless to prepare real-world web content for use in LLM pipelines.
Key Features
- Instant Usage: Just add
llmstxt.new/before any URL. - Two Outputs:
llms.txtfor concise summaries,llms-full.txtfor full content. - API Friendly: Call via
http://llmstxt.new/{YOUR_URL}or with a Firecrawl API key for full output. - LLM-Ready Format: Designed for both training and inference contexts.
Day 3 – /extract v2
Overview
Today we’re launching /extract v2, a major upgrade to our extraction system — powered by the FIRE-1 agent. With full support for pagination, multi-step flows, and dynamic interactions, extract v2 goes way beyond what we shipped back in January. It’s also now possible to extract data without a URL, using a built-in search layer to find the content you’re after. We’ve rebuilt the internals from the ground up — improved models, better architecture, and significantly better performance across our internal benchmarks.
Key Features
- FIRE-1 Integration: Automatically handles page actions, navigation, and interaction.
- Multi-Page Extraction: Extract data across paginated or step-based flows.
- No URL Required: Use built-in search to extract content without a direct link.
- Improved Accuracy: New models and architecture mean better, faster results.
Day 2 - FIRE-1 Agent
Overview
Meet FIRE-1, Firecrawl’s first AI Agent built to take web scraping to the next level. With intelligent navigation and interaction capabilities, FIRE-1 can go far beyond traditional scraping methods. From handling pagination to interacting with dynamic site elements like buttons and links, FIRE-1 allows for powerful, context-aware scraping and extraction workflows.
Key Features
- Smart Navigation: Move through paginated or multi-step content automatically.
- Dynamic Interaction: Click buttons, follow links, and interact with JavaScript-rendered components.
Day 1 - Change Tracking
Overview
Change tracking is a powerful feature that allows you to monitor and detect changes in web content over time. It is available in both the JavaScript and Python SDKs.
Key Features
- Detect Changes: Identify if a webpage has changed since the last scrape.
- View Specific Changes: Access detailed information about what has changed between scrapes.
- Structured Data: Receive structured data about the changes.
- Visibility Control: Manage the visibility of changes on your website.
changeTracking format, you can effectively monitor changes on a website and receive comprehensive information about the timestamp of the previous scrape, the result of the comparison between the two page versions, and the visibility of the current page/URL.
Day 0 - Firecrawl Editor Theme
