Do coding agents recommend Vapi?
Vapi was chosen in 16% of 754 judged voice agents sessions, ranking second. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Vapi was chosen in 16% of 754 judged voice agents sessions, ranking second. It was also raised as a candidate in 467 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 voice agents inside a realistic codebase. Not what a chat assistant says about Vapi. What an agent actually installed.
The numbers
| Category | Voice agents |
| Sessions in the category | 754 |
| Sessions where Vapi was chosen | 124 |
| Install share | 16% |
| Rank in category | 2 of 32 |
| Codebases it won in | 10 |
| Raised as a candidate, not chosen | 467 |
| Chosen when considered | 21% |
| Site | vapi.ai |
By agent
The agents treat Vapi very differently. Cursor chose it in 29% of its sessions in this category and Grok Build CLI in 5%, a spread of 24 points.
| Agent | Sessions | Chose Vapi | Share |
|---|---|---|---|
| Claude Code | 157 | 17 | 11% |
| Codex | 217 | 44 | 20% |
| Cursor | 167 | 49 | 29% |
| Grok Build CLI | 60 | 3 | 5% |
| Muse Code | 153 | 11 | 7% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Grok Build CLI, your real position here is 5%, not 16%.
By who was asking
Vapi does much better with one kind of buyer than another. It won 27% of sessions asked as junior developer and 3% of those asked as enterprise team.
| Who is asking | Sessions | Chose Vapi | Share |
|---|---|---|---|
| Vibe coder | 134 | 34 | 25% |
| Junior developer | 90 | 24 | 27% |
| Senior engineer | 322 | 60 | 19% |
| Enterprise team | 208 | 6 | 3% |
What Vapi was up against
The full ranking in voice agents, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Retell AI | 168 | 22% |
| 2 | Vapi (this page) | 124 | 16% |
| 3 | Twilio ConversationRelay | 99 | 13% |
| 4 | LiveKit Agents | 98 | 13% |
| 5 | ElevenLabs Agents | 59 | 8% |
| 6 | OpenAI Realtime API | 49 | 6% |
| 7 | Built in-house (no product adopted) | 35 | 5% |
| 8 | Grok Voice Think Fast 2.0 | 29 | 4% |
What this means
A solid second or third position in a category means the agent is genuinely choosing rather than reaching automatically. That is a winnable position, because the inputs it uses can be changed.
The fastest gains are usually in the sessions that were nearly won: read them, find the step where the agent moved on, and fix that step.
Where these numbers come from
The 754 sessions in voice agents are part of a published set of 15,287, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every voice agents run can be replayed on the board.
If you work on Vapi: 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 Vapi?
Yes. Vapi was chosen in 124 of the 754 judged sessions in voice agents, a 16% install share, ranking second in its category.
Does Claude Code recommend Vapi?
In 17 of the 157 sessions in voice agents run with Claude Code, which is 11%.
Do different coding agents treat Vapi differently?
Yes, and by a wide margin. Cursor chose it in 29% of its runs and Grok Build CLI in 5%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 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 Vapi considered but not chosen?
It was raised as a candidate in 467 sessions without being chosen, and chosen in 124. That is a 21% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.