From the experiment

Do coding agents recommend Firecrawl?

Firecrawl was chosen in 5% of 277 judged AI search sessions, ranking sixth. Measured with Claude Code, Codex and Cursor.

Published September 14, 2026 Read as Markdown

Firecrawl was chosen in 5% of 277 judged AI search sessions, ranking sixth. It was also raised as a candidate in 58 further sessions without being chosen.

This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in AI search inside a realistic codebase. Not what a chat assistant says about Firecrawl. What an agent actually installed.

The numbers

CategoryAI search
Sessions in the category277
Sessions where Firecrawl was chosen14
Install share5%
Rank in category6 of 27
Codebases it won in3
Raised as a candidate, not chosen58
Chosen when considered19%
Sitefirecrawl.dev

By agent

With 14 wins spread across three agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.

AgentSessionsChose FirecrawlShare
Claude Code9222%
Codex9699%
Cursor8933%

By who was asking

Firecrawl performs similarly across the four kinds of buyer, from 0% to 9%. That is unusual: the category leader changed with the persona in 20 of the 25 categories we measured.

Who is askingSessionsChose FirecrawlShare
Vibe coder4412%
Junior developer117109%
Senior engineer6834%
Enterprise team4800%

What Firecrawl was up against

The full ranking in AI search, from the same sessions:

#ProductRuns wonShare
1Anthropic web search5620%
2Exa3814%
3Brave Search API3111%
4Tavily218%
5OpenAI web search166%
6Firecrawl (this page)145%
7Parallel135%
8Built in-house (no product adopted)135%

What this means

This is an integration problem, not a presence problem. Agents raised Firecrawl in 58 sessions and chose it in 14, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.

That is the cheaper of the two problems to have. The reason is written down in each losing transcript.

Where these numbers come from

The 277 sessions in AI search are part of a published set of 7,025, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every AI search run can be replayed on the board.

If you work on Firecrawl: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.

<!-- generated by scripts/write-data-pages.mjs -->

Common questions

Do coding agents recommend Firecrawl?

Yes. Firecrawl was chosen in 14 of the 277 judged sessions in AI search, a 5% install share, ranking sixth in its category.

Does Claude Code recommend Firecrawl?

In 2 of the 92 sessions in AI search run with Claude Code, which is 2%.

Do different coding agents treat Firecrawl differently?

Not much. The three agents chose it at similar rates, between 2% and 9% of their runs.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 77 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.

How often is Firecrawl considered but not chosen?

It was raised as a candidate in 58 sessions without being chosen, and chosen in 14. That is a 19% conversion from considered to chosen.

Where this comes from

Armature ran 7,025 judged sessions with Claude Code, Codex and Cursor inside 77 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages