Firecrawl /agent is a magic API that searches, navigates, and gathers data from even the most complex websites. Describe what data you want and agent handles the rest. Find information in hard-to-reach places, return single datapoints or entire datasets at scale.
Hey Product Hunt 👋
We're Eric, Caleb, and Nick from Firecrawl. Today we're launching /agent, an API that can gather data wherever it lives on the web.
Traditional web extraction requires exact URLs and only scrapes what's on that page. But real data is scattered. It lives across sites, buried in paginated catalogs, hidden in multi-step flows, and you rarely know the exact URLs upfront.
We built /agent to handle this autonomously. Just describe what data you need, with or without a URL, and it figures out the rest. It searches, navigates, and gathers information from the widest range of websites, reaching data no other API can. Whether you need one data point or entire datasets at scale, it just works.
It's live now in the Firecrawl API and SDKs, and coming soon to n8n, Zapier, and our MCP.
You can try it out in our playground: https://www.firecrawl.dev/app/agent
Would love to hear what you think.
P.S. Launching in research preview, expect improvements as we gather feedback.
I tried it and as a non technical user this has given great initial results. I will share more here once my product is built, but consider me a new customer!
/agent feels like a big step beyond “URL-in, HTML-out” scraping — the idea of describing intent and letting the system search, navigate, and collect autonomously is super compelling. This solves so many real-world data gaps.Curious: how does /agent decide when to stop exploring vs. keep going, especially for large or ambiguous data requests?
`/agent` is so good – congrats on the launch! We're happy paying customers at Dub 😁
I've been using Firecrawl for several side projects, really amazing tool. Agent is the next logical frontier in their development. Can't wait to try this more extensively.
Awesome stuff Eric! We've been using the structured data in the single URL scraping data for a while with great results so excited to checking out how much deeper /agent can go and what info we can unlock
I love this! ❤️ Congrats on the launch. I'm already using it for one of my apps in production and got great feedback so far. Keep it up 🚀
Outstanding, this is an amazing product. I'm literally in the process right now of setting up that API in my application to pull down leads. I'll let you know how that goes later. Amazing product, good job
Been hacking together scrapers for docs and pricing pages. Always breaks. This looks like a saner path: give it a URL, get markdown/JSON. Curious how it handles login walls and messy JS tables. If it’s stable, I’ll gladly bin my puppeteer scripts.
Amazing product and team! Great to see how you and the team are executing!
Wow, what a this thing is off the hook. I love the graphics I love the concept, I love what it does, and yes, I signed up and am getting ready to test this thing out right now
I really like the autonomous search and navigation idea. One thing that could be powerful for teams is transparency, will users be able to see or replay how the agent found the data, especially for debugging or trust?
This is certainly an interesting idea. We have previously built some data mining capabilities using agents as well.
In fact, if you use Claude Code and provide it with sufficient website access, a terminal, a browser, or even its built-in web search tools, it seems capable of retrieving the same unstructured information you want. The only extra step is converting that into structured data. How does your solution differ from this approach?
In my opinion, the most critical factor is how to turn the entire extraction process into a standardized script. This is the true purpose of a web crawler:
1. To take repetitive tasks that would otherwise be costly and labor-intensive.
2. To use script-based automation to lower the cost of repeated crawls.
3. To maintain the ability to update incremental data efficiently.
How are you thinking about this particular aspect?
Really interesting. I would love to use it. Where is the scraped data stored and how do you chunk it?
Just tried the playground on a gnarly site — got usable Markdown fast and it saved me time. Excited for the n8n/Zapier hookups you mentioned. Keep shipping! 🔥
About /agent by Firecrawl on Product Hunt
“Gather structured data wherever it lives on the web”
/agent by Firecrawl launched on Product Hunt on December 23rd, 2025 and earned 596 upvotes and 34 comments, earning #2 Product of the Day. Firecrawl /agent is a magic API that searches, navigates, and gathers data from even the most complex websites. Describe what data you want and agent handles the rest. Find information in hard-to-reach places, return single datapoints or entire datasets at scale.
/agent by Firecrawl was featured in Developer Tools (511k followers), Artificial Intelligence (466.1k followers) and Data (2.3k followers) on Product Hunt. Together, these topics include over 153.5k products, making this a competitive space to launch in.
Who hunted /agent by Firecrawl ?
/agent by Firecrawl was hunted by Eric Ciarla. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how /agent by Firecrawl stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Eric Ciarla