Mark Mercer

Chief of Staff @ Firecrawl

[Nicolas Camara @nickscamara_]

opus 4.8 dropped today. you could've found out minutes before anthropic announced it.

a firecrawl monitor on their entire website emails you the second a new model id appears, before the announcement.

you can build this today

[Michael Grinich @grinich]

Today WorkOS is launching auth.md

An open protocol for agents to register for services on the web.

We're partnering with @Cloudflare and @Firecrawl as some of the first providers.

Why did we build this? And why now? 🧵

[Firecrawl @firecrawl]

The web wasn't built for AI agents. So we built Firecrawl.

- /search finds fresh, relevant sources from the web
- /scrape turns any URL into clean context for AI
- /interact automates clicks, pagination, and logins

Join 1,000,000+ developers connecting intelligence to the web.

[Nicolas Camara @nickscamara_]

One html page on avg produces 36k tokens. With proper md conversion you cut that down to 2.8k tokens. That’s 92% cost reduction

While I agree that some cases HTML is better, by no means it’s a cost viable option for 99.9% of users

You literally save $1,079* if u fetch 10k pages

[Caleb Peffer (Hiring!) @CalebPeffer]

Want to own our /Search product?

Build. Talk to customers.

All with Firecrawl at your back

apply here => https://t.co/9HvO58sZBv

[Mark Mercer @MarkAtFirecrawl]

I joined Firecrawl as employee #12. No HR. No recruiting. No onboarding. No ops. No events.

My background? Theater and education. Not tech.

The thing I have to constantly remind myself: Trust yourself. You can do anything.

9 months later:

→ Built the entire recruiting function from zero. 80+ screens across 12 roles in the last 4 weeks alone.
→ Created Firecrawl After Dark — our monthly developer event series. Brand, format, execution. All mine.
→ Planned and executed three full company offsites for a global team — from scratch, no template, no events team.
→ Stood up global payroll and contractor ops across multiple countries.
→ Shipped a branded swag campaign to 50+ countries.
→ Built a timezone wall in HQ showing every team member. The details matter.

13 years of directing 2,500+ performers and managing 1,000+ volunteers taught me more about startup ops than most people would expect.

The job isn't a function. It's owning whatever the company needs before it knows it needs it.

We're hiring → https://t.co/IytzN52Xhz

[Firecrawl @firecrawl]

New from Firecrawl last month:

- /interact lets agents scrape a page then click, type, and navigate in natural language
- Java SDK adds scrape, search, and crawl to any Java project
- @opencode plugin brings the Firecrawl CLI to OpenCode agents

[Firecrawl @firecrawl]

Introducing the /interact endpoint

- Just /scrape a page
- Call /interact to do any action with natural language
- Watch agents click, fill, scroll to get deep web data

Available today.

[Thierry Damiba @ptdamiba]

Excellent example of community done right by @firecrawl tonight at their After Dark event.

Builders working on everything from alternative data for prediction markets to car listing intelligence sharing ideas over @CelsiusOfficial and pizza.

Big thanks to @MarkAtFirecrawl for organizing.

And they have a Fireclaw!

[Firecrawl @firecrawl]

Introducing Firecrawl After Dark 🌑

An exclusive, invite-only event for 10x engineers building with web data.

This Wednesday. 7pm-1am. Food + unlimited coffee and Celsius on us.

[Firecrawl @firecrawl]

Introducing the new Firecrawl CLI 🔥

The toolkit for agents to scrape, search, and browse the web.

- Scrape clean data from any page
- Search the web and get full results back
- Spin up cloud browsers for interactive flows

npx -y firecrawl-cli@latest init --all --browser

[Mark Mercer @MarkAtFirecrawl]

@firecrawl Noooiiiiceee.

[Firecrawl @firecrawl]

The internet is full of valuable data - but most of it is buried in massive archives.

With our browser, you can turn those archives into your own custom knowledge base in seconds.

Like this dataset of vintage software from 1990–1998 👇

[Nicolas Camara @nickscamara_]

Lately my research workflow got 10x better by using Claude agent teams and basically treating the filesystem + firecrawl as a web data toolkit:

→ (1) search + scrape for fast mapping + relevant content
→ (2) real browser environments when pages need interaction or need sessions to be persisted (clicks, pagination, auth)
→ (3) parallel agents write their findings back into the repo (notes, citation, etc)

You get faster + more accurate results, and everything lands locally so any agent can resume where it left off

[Nicolas Camara @nickscamara_]

We just shipped a new 'Get Code' for our browser sandbox 📦

Easily integrate with @aisdk @LangChain @claudeai

[Firecrawl @firecrawl]

We launched Browser Sandbox last week, and the community response has been incredible 👀

Agents and Devs have already spun up tens of thousands of browsers, executed live code inside them - all through Firecrawl.

Here's some of the most popular domains 👇

[Mark Mercer @MarkAtFirecrawl]

@leonardogrig @firecrawl We built this city… we built this city on Firecrawl.

[Mark Mercer @MarkAtFirecrawl]

@nickscamara_ @firecrawl Lets goooooooooo

[Nicolas Camara @nickscamara_]

our next project: browser sandbox

a secure browser environment for agents to interact with the web

→ zero config
→ loaded with agent-browser + playwright
→ agents can safely exec bash, py, js to control the browser
→ works with any agent like claude code, openclaw, codex

[Firecrawl @firecrawl]

Firecrawl Skill, now in GPT-5.3 Codex 🔥

Give Codex clean, real-time web data for your coding workflows.