Do coding agents recommend Brave Search API?
Brave Search API was chosen in 11% of 277 judged AI search sessions, ranking third. Measured with Claude Code, Codex and Cursor.
Brave Search API was chosen in 11% of 277 judged AI search sessions, ranking third. It was also raised as a candidate in 73 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 Brave Search API. What an agent actually installed.
The numbers
| Category | AI search |
| Sessions in the category | 277 |
| Sessions where Brave Search API was chosen | 31 |
| Install share | 11% |
| Rank in category | 3 of 27 |
| Codebases it won in | 10 |
| Raised as a candidate, not chosen | 73 |
| Chosen when considered | 30% |
| Site | brave.com |
By agent
The three agents agree closely on Brave Search API, choosing it at rates within 3 points of each other.
| Agent | Sessions | Chose Brave Search API | Share |
|---|---|---|---|
| Claude Code | 92 | 10 | 11% |
| Codex | 96 | 12 | 13% |
| Cursor | 89 | 9 | 10% |
By who was asking
Brave Search API performs similarly across the four kinds of buyer, from 6% to 17%. That is unusual: the category leader changed with the persona in 20 of the 25 categories we measured.
| Who is asking | Sessions | Chose Brave Search API | Share |
|---|---|---|---|
| Vibe coder | 44 | 3 | 7% |
| Junior developer | 117 | 16 | 14% |
| Senior engineer | 68 | 4 | 6% |
| Enterprise team | 48 | 8 | 17% |
What Brave Search API was up against
The full ranking in AI search, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Anthropic web search | 56 | 20% |
| 2 | Exa | 38 | 14% |
| 3 | Brave Search API (this page) | 31 | 11% |
| 4 | Tavily | 21 | 8% |
| 5 | OpenAI web search | 16 | 6% |
| 6 | Firecrawl | 14 | 5% |
| 7 | Parallel | 13 | 5% |
| 8 | Built in-house (no product adopted) | 13 | 5% |
What this means
Brave Search API was raised in 73 sessions and chosen in 31. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.
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 Brave Search API: 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 Brave Search API?
Yes. Brave Search API was chosen in 31 of the 277 judged sessions in AI search, a 11% install share, ranking third in its category.
Does Claude Code recommend Brave Search API?
In 10 of the 92 sessions in AI search run with Claude Code, which is 11%.
Do different coding agents treat Brave Search API differently?
Not much. The three agents chose it at similar rates, between 10% and 13% 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 Brave Search API considered but not chosen?
It was raised as a candidate in 73 sessions without being chosen, and chosen in 31. That is a 30% 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.