Introducing Firecrawl MCP v3.
Give your agents access to all of the knowledge they need.
→ 3000+ tools with automatic provider waterfalls
→ 60x higher rate limits
→ 4x more usage
→ Spawn subtasks for parallel work
Available now for every harness.
https://t.co/3c4LhoiJ4y
Firecrawl now indexes 3,000,000+ research papers, including every major AI/ML paper.
Your agents can find the right paper, even one posted today, and read its full text.
Run your next lit review from any harness with the Firecrawl plugin.
https://t.co/B2AVy8jxWU
Introducing job search tools for ChatGPT & Claude.
→ Match your resume to 7M+ open roles
→ Find hiring managers to email from 250M+ people
→ See what they care about before you reach out
Run your job hunt from any harness with the Firecrawl plugin.
https://t.co/hkV9aMOKkU
Sunil Bharti Mittal recounts the telecom shakeout of 2016, when billions of dollars in investments were wiped out and companies disappeared. He tells @FLacqua how he doubled down, acquired assets and raised $18 billion in 34 months, betting that surviving the storm would make Bharti Airtel stronger than ever https://t.co/xit9g8lOR9
Introducing our free life science research index.
Give your ChatGPT, Claude & Grok agents access to 41M+ papers, from drug discovery & clinical trials to gene studies.
Take any life science question from hypothesis to evidence with the Firecrawl plugin.
https://t.co/BSUaC2QzZ3
We're teaming up with Benzinga to bring licensed, real-time financial data to AI agents.
Alexandria is where agents get data straight from official providers, and it now includes Benzinga news, analyst ratings and unusual options activity.
https://t.co/rGMxXb1GHP
"Close enough" doesn't work for legal search.
So we measured it: 581 requests for one specific official source each. Our index put the right one first 76.2% of the time, #1 on the benchmark. #SearchWithFirecrawl
Today we're launching the Legal Retrieval Benchmark.
581 search requests, each for one official source like a statute, regulation, bill or agency doc.
Our Government & Legal Index ranked #1, with the right source as its top result 76.2% of the time.
https://t.co/hYTrmOKUsm
Election night, but your agent actually has the data.
Results, campaign funding & voting records for 470 House & Senate races. Free in Alexandria.
Introducing free Election Records in Alexandria 🇺🇸
Ask your agent about 470 House & Senate races:
- Results as each state reports
- Who funds each campaign
- How incumbents voted
Try it with the Firecrawl plugin in ChatGPT, Claude, Grokbot, & beyond.
https://t.co/kOr7Z8dql8
Enrichment usually means another tab, another table, another tool to babysit.
Now your agent just does it: 250M+ people & 26M+ companies, right inside ChatGPT or Claude.
Introducing headless Clay for agents.
→ Search 250M+ people & 26M+ companies
→ Get emails, job & company data
→ 1000 credits/month free
→ 88% cheaper than Clay at scale
Run all of your enrichment flows in ChatGPT, Claude, Grokbot, and beyond!
https://t.co/pVrxIyAENy
Firecrawl is now live in @eve, Vercel's open-source agent framework 🔥
One command gives your agents the web and beyond with Alexandria.
https://t.co/1EuFFHJ6EF
Your coding agent's idea of a "safe" package is frozen at its training cutoff.
Now Codex & Claude Code can check live: 400K+ vulnerabilities, the latest advisories from NVD, CISA & GitHub, and patch before attackers find them.
Introducing Cybersecurity Data in Alexandria 🔒
Your Codex & Claude Code agents can now:
→ Check your code's dependencies for 400,000+ vulnerabilities
→ Find the latest advisories from NVD, CISA & GitHub
→ Patch them before attackers find them
https://t.co/aJsqoZMSdR
Introducing Directory, free recruiting data for ChatGPT & Claude.
Describe a role & get a shortlist from 250M+ profiles in Alexandria, with experience & work emails.
Start sourcing with 1,000 free credits a month in the Firecrawl plugin.
https://t.co/pVrxIyAENy
Introducing Jev + Firecrawl company data
Pull company records from Alexandria and let Jev classify them.
We sorted 146 startups by who buys from them in 2.2 seconds.
Perfect for lead scoring, account research & market maps at lightning speed!
https://t.co/y5UeKLimrx
Ever tried to figure out a city permit rule or a local tax requirement with an AI? It usually guesses.
Now it can just look it up: federal statutes down to municipal codes, 30M+ pages, free in ChatGPT & Claude.
Introducing the free Government & Legal Index for ChatGPT & Claude.
Give your AI agents 30M+ US government pages, from federal statutes and court opinions to city codes and permits.
Research tax rules, permits & case law with the Firecrawl plugin.
https://t.co/WT268coAo9
Smarter models won't fix your AI agent.
Better data access will.
That's why we built Alexandria, a knowledge library for superintelligence: 82 providers, 471 capabilities & 113M+ indexed sources behind one connection.
Congrats Caleb, Eric & Nick for Series B raise. Lets Go!
Introducing Alexandria.
We raised a $75M Series B led by Smash Capital to build the world’s largest knowledge library for superintelligence.
Supercharge your agents with instant access to the most powerful data sets & providers.
https://t.co/ptd6I04Kmh
Congrats to @CalebPeffer, @ericciarla, @nickscamara_, and @firecrawl on their $75M Series B!
Firecrawl turns the web into clean, structured data for AI agents, with more than 1.5 million people building on their API.
They're also launching Alexandria, a knowledge library where agents can search the live web, official data providers, and dedicated indexes of scientific papers, developer docs, and government records. Providers get paid when agents use their data, and Firecrawl plans to open that up to anyone with knowledge worth sharing.
https://t.co/sScCgFgvkZ
Announcing the Artificial Analysis Search Index, benchmarking how search API providers perform on quality, cost, and speed when used by an agent. We are initiating coverage with Parallel, Exa, Firecrawl, You (dot) com, Tavily, Keenable, and Brave
Search is one of the most important tools for agents. Search providers make different choices about how they search, rank, and package results, and those choices change what the model reads and how it acts. We are expanding our benchmarking coverage to search APIs, so developers can pick a search provider on measured quality, cost, and speed.
Each provider result pairs a search API provider with the same model, GPT-5.6 Luna (medium). The model runs inside Stirrup, our open-source agent harness, with tools for searching and fetching pages from the web - only the search provider behind the search tool changes.
At launch, the leaderboard covers 11 results across 7 search providers, and we’ll keep expanding coverage as we look to provide the most accurate and comprehensive benchmarking of search providers for AI agent usage.
Key elements of the Artificial Analysis Search Index:
➤ Three equally weighted benchmarks: the Search Index is the average of DeepSearchQA (900 broad research questions that need many searches, graded with an F1 score over answer items), BrowseComp (a 200-sample hard subset of facts that need multi-hop browsing), and AA-Omniscience (a 600 question private subset, balanced across 6 domains)
➤ Same agent, different search provider: the agent has 25 turns available to complete each task. Its web search tool returns the search provider's native response payload (with content modes standardized to snippets), with a maximum of 10 results and contamination sources filtered out
➤ Model-only baseline: we compare search agent results to the same model answering single-shot without tools, showing how much each provider lifts the model above its internal knowledge
➤ Cost and Time per Task: we aggregate the time and cost spent on both model inference and search. This is key - search APIs have different cost and latency structures, but these can be offset where they help an agent use fewer turns and save on costly language model inference
Key results:
➤ Parallel, Exa, and Firecrawl have the strongest overall performance, with Artificial Analysis Search Index scores of 75, 74, and 73 respectively at launch
➤ All search providers tested substantially improve knowledge-based benchmark performance: the model only baseline scores 33 on the Search Index, while search-included provider results score between 65 and 75
➤ Focused search results reduce spend on model inference: Parallel Search (advanced) search costs more per task than Parallel Search (basic) but less per task in total ($0.084 vs $0.11). Higher quality results cut the model's token use by over 40% in this case, more than offsetting increased search costs while reaching higher benchmark scores
➤ Fast search calls do not guarantee fast tasks: Parallel Search (turbo) has the fastest average search calls among Parallel's tiers (0.51s per query vs 1.03s for Parallel Search (basic)) but the basic tier scores higher on quality (73 vs 67) and the two land close on total time per task
Introducing Firecrawl Developer Index, an index for supercharging coding agents.
Search 70M+ primary sources including repos, docs, & issues with the highest recall of any coding-specific index.
Ensure agents ship correct, up-to-date code every time!
https://t.co/i3rH3PiKFu