Noaa

Member of Technical Staff at @firecrawl.

Shipping web data tooling for agents.
/search /scrape /crawl /extract /interact.

[Noaa @firenoaa]

I’m Noaa, I build at @firecrawl.

I’ll post shipping notes from integrations work: Stripe Projects, Vercel Marketplace, auth exchange, billing edges, logging, schema validation.

If you ship the same glue, I want your war stories.

[Noaa @firenoaa]

@abimaelmartell @sentry Super cool! Where do I 😂

[Noaa @firenoaa]

@firecrawl If you averaged 20 minutes per paper, 41 million papers would take about 1,560 years reading 24/7.

At a more human 8 hours/day, 5 days/week, it’s roughly 6,600 years.

6,600 years of knowledge at the robot's fingertips is crazy 🔥

[Noaa @firenoaa]

lfggg!!

[Firecrawl @firecrawl]

We just added 41M+ life science papers to the Firecrawl Research Index.

Your AI agents can now search drug discovery, clinical trial, and biology literature with 90% recall@10.

All sourced from authoritative sources and 100% free. Live in the API via /search/research.

[Noaa @firenoaa]

We’re live in @opencode!

BYOV - bring your own vibe; no key needed thanks to keyless 🚀

[Firecrawl @firecrawl]

Firecrawl is now a keyless option for web search in @opencode 🔥

Set us as your search provider & your AI agents get live results with state-of-the-art accuracy (94.7% on SimpleQA), no API key or signup at all.

Just update opencode2, select Firecrawl, & start searching today!

[Gergő Móricz @gergomoricz]

Anthropic launches Claude Tag, XAI launches Grok Bot, Spotify launches Xirp, Doordash launches Flux.

We already built all these tools in January for internal use at Firecrawl.

If you'd like to work at a startup that's 6 months ahead of the game: https://t.co/Zoo1Uxlkl4

[Eric Ciarla (hiring) @ericciarla]

Empower your Codex agents with the best web context on the planet!

[Firecrawl @firecrawl]

Firecrawl is now in the top 50 GitHub repos of all time!

All because agents need a better way to gather context on the web.

And we're just getting started 🔥

[Nicolas Camara @nickscamara_]

anydoc can now run fully in your browser

parse pdf, docx, pptx and 10 more formats into clean markdown in ms

nothing gets uploaded. 500 files → 1.7s. tons of fixes shipped

100% open source

try here: https://t.co/gF1leRHDRN

[Noaa @firenoaa]

@gergomoricz It’s all a conspiracy by rhe ink companies to stay in power muhahaa

[Noaa @firenoaa]

@DustinKingen @munoncode @firecrawl @OpenAI We shipped a change a couple of hours ago, please try again and lmk if it doesn’t work still!

[Noaa @firenoaa]

@munoncode @firecrawl @OpenAI We shipped a change a couple of hours ago, please try again and lmk if it doesn’t work still!

[Noaa @firenoaa]

@munoncode @firecrawl @OpenAI Heya Martin, does it consistently fail with the same error?

[Abimael Martell @abimaelmartell]

Local document parsing built in on Hermes Agent powered by our new rust library!

https://t.co/Oq04CdcrPU

Lets go!

🔥

[Garry Tan @garrytan]

Make something agents want

[Nicolas Camara @nickscamara_]

introducing anydoc

now your agents get 100x faster local parsing for pdf, docx, pptx & 10 more formats

- sub-5ms md conversion
- 500 docx files in 1.7s
- top quality across all 13 formats
- rust-based
- open source

already powering @firecrawl /parse

https://t.co/fVsRsYFNyC

[Firecrawl @firecrawl]

Today we're launching anydoc, our new Rust-based doc parsing engine 🔥

sub ~5ms markdown parsing for PDFs, Word docs, slide decks, and 10 other formats with best in class quality.

100% open source and powering our /parse endpoint!

[Noaa @firenoaa]

Game changer 💯💯💯

[Nicolas Camara @nickscamara_]

we built pdf-inspector so agents can process PDFs without waiting on OCR. it classifies any PDF in ~20ms and extracts clean markdown locally

→ 200 PDFs processed in 2.8s
→ top quality in extracting tables + graphs
→ built in rust
→ open source

https://t.co/Wjp9kpTHXJ

[Noaa @firenoaa]

This is huge!

[Firecrawl @firecrawl]

Introducing the new Firecrawl MCP 🔥

It now uses 50% less context on every /search, /scrape, and /interact call.

Plus, instant onboarding with OAuth for humans and a keyless version for agents.

Get agent-ready web context in any MCP client today: https://t.co/F1iHuvkJ5f

[Noaa @firenoaa]

Welcome @Replit to our partnership ecosystem 🔥 🚀

[Firecrawl @firecrawl]

Firecrawl is now an official @Replit Connector 🔥

Get high quality web context into your Replit apps with Firecrawl /search, /scrape, and /interact, all set up in a single click.

Connect today and claim 10,000 free Firecrawl credits!