There's a $50B company built on web scraping.
No capital. No strategy. Just 3 hungry students solving a delivery problem.
Their edge? Smart web scraping to gather restaurant data.
Co-Founder @ Firecrawl (YC S22). Previously Mendable.
Joined March 2022
- Introducing o1 web crawler ๐ธ๏ธ It crawls entire websites with OpenAIโs new o1 reasoning model and @firecrawl . Just state an objective and it will navigate + return the requested data in a JSON schema. Check it out:
00:00 - Introducing Open Lovable v2 - an open source AI software engineer. Just search for a website and agents will create a working clone you can build on top of. Now powered by @firecrawl search, @vercel Sandbox, and Kimi K2 on @GroqInc. Fork the 100% open source example:
00:00 - Introducing llms.txt Generator โจ You can now concatenate any website into a single text file that can be fed into any LLM. We crawl the whole website with @firecrawl and extract data with gpt-4o-mini. Create your own llms.txt at llmstxt.firecrawl.dev!
00:00 - Introducing o1 Trend Finder ๐ฆ Use o1 to monitor & notify you of trending topics on social media. It gets posts from key influencers, finds any trends, then pings you in slack. It's been game changer for marketing at @firecrawl and will help us scale content in 2025.
00:00 - Instantly clone any website with Cursor and Firecrawl ๐ฅ Just enter the site you want to clone into @cursor_ai composer and the agent will clone it after visiting the site. Powered by Claude 3.5 Sonnet and our new @firecrawl MCP server.
00:00 - Next week we're dropping Open Lovable v2 - an open source AI software engineer. Just paste in a website URL and AI agents will create a working clone you can build on top of, all completely open source and powered by @firecrawl. Stay tuned to see all of the new features ๐
00:00 - Introducing new Sonnet crawlerโก๏ธ Crawl any website with Anthropicโs new 3.5 model and batch scrape from @firecrawl. Enter an objective and the crawler returns data in a structured format. It's faster than o1 crawler and has monitoring by @AgentOpsAI! Demo & tutorial:
00:00 - Introducing DeepSeek R1 web crawler ๐ It crawls entire websites with the R1 reasoning model and @firecrawl's /extract. Watch R1 select URLs and filter results while /extract scans for the structured data on the websites. Check it out:
00:00 - We're dropping an open source Clay competitor next week ๐ Just upload a CSV with emails and empty columns, then AI agents powered by @firecrawl will find and fill in the missing information. Find decision makers, company size, tech stack, and more. Stay tuned!
00:00 - Introducing Swarm Web Extractor ๐ค Based on an objective, it autonomously searches the web, maps entire websites, and extracts data. Built with OpenAIโs new multi-agent framework Swarm, @serp_api, and @firecrawl. Check it out:
00:00 - Generate AI podcasts based on real time news๐๏ธ I built an app that crawls the web for interesting news stories then records a podcast with my own voice. Powered by Llama 3.1 from @togethercompute, voice cloning from @play_ht, and scraping from @firecrawl. Check it out:
00:00 - Anthropic's New Computer Use API can fill out job applications โ๏ธ Watch @AnthropicAI's new API use @firecrawl to quickly gather information and then take action filling out part of a real job application. Check it out (hosted on @Replit):
00:00



