Do coding agents recommend Firecrawl?
Firecrawl was chosen in 5% of 639 judged AI search sessions, ranking sixth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Firecrawl was chosen in 5% of 639 judged AI search sessions, ranking sixth. It was also raised as a candidate in 93 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code 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
| Category | AI search |
| Sessions in the category | 639 |
| Sessions where Firecrawl was chosen | 31 |
| Install share | 5% |
| Rank in category | 6 of 42 |
| Codebases it won in | 4 |
| Raised as a candidate, not chosen | 93 |
| Chosen when considered | 25% |
| Site | firecrawl.dev |
By agent
Claude Code, Codex, Cursor, Grok Build CLI and Muse Code land within 8 points of each other on Firecrawl, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose Firecrawl | Share |
|---|---|---|---|
| Claude Code | 140 | 2 | 1% |
| Codex | 192 | 18 | 9% |
| Cursor | 136 | 5 | 4% |
| Grok Build CLI | 35 | 2 | 6% |
| Muse Code | 136 | 4 | 3% |
By who was asking
Firecrawl performs similarly across the four kinds of buyer, from 1% to 8%. That is unusual: the category leader changed with the persona in 23 of the 31 categories we measured.
| Who is asking | Sessions | Chose Firecrawl | Share |
|---|---|---|---|
| Vibe coder | 106 | 1 | 1% |
| Junior developer | 208 | 16 | 8% |
| Senior engineer | 157 | 13 | 8% |
| Enterprise team | 168 | 1 | 1% |
What Firecrawl was up against
The full ranking in AI search, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Exa | 92 | 14% |
| 2 | Brave Search API | 89 | 14% |
| 3 | Anthropic web search | 86 | 13% |
| 4 | Tavily | 79 | 12% |
| 5 | OpenAI web search | 32 | 5% |
| 6 | Built in-house (no product adopted) | 32 | 5% |
| 7 | Firecrawl (this page) | 31 | 5% |
| 8 | Parallel | 29 | 5% |
What this means
This is an integration problem, not a presence problem. Agents raised Firecrawl in 93 sessions and chose it in 31, 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 639 sessions in AI search are part of a published set of 15,051, 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 31 of the 639 judged sessions in AI search, a 5% install share, ranking sixth in its category.
Does Claude Code recommend Firecrawl?
In 2 of the 140 sessions in AI search run with Claude Code, which is 1%.
Do different coding agents treat Firecrawl differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 1% and 9% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 92 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 93 sessions without being chosen, and chosen in 31. That is a 25% conversion from considered to chosen.
Where this comes from
Armature ran 15,051 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 92 realistic codebases, and published every run. The numbers on this page come from that work.