Do coding agents recommend Vapi?
Vapi is the most chosen voice agent platform, taking 24% of 308 judged voice agents sessions. Measured with Claude Code, Codex and Cursor.
Vapi is the most chosen voice agent platform, taking 24% of 308 judged voice agents sessions. It was also raised as a candidate in 179 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor 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 | 308 |
| Sessions where Vapi was chosen | 74 |
| Install share | 24% |
| Rank in category | 1 of 18 |
| Codebases it won in | 8 |
| Raised as a candidate, not chosen | 179 |
| Chosen when considered | 29% |
| Site | vapi.ai |
By agent
The three agents treat Vapi very differently. Cursor chose it in 39% of its sessions in this category and Claude Code in 15%, a spread of 24 points.
| Agent | Sessions | Chose Vapi | Share |
|---|---|---|---|
| Claude Code | 94 | 14 | 15% |
| Codex | 110 | 19 | 17% |
| Cursor | 104 | 41 | 39% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Claude Code, your real position here is 15%, not 24%.
By who was asking
Vapi does much better with one kind of buyer than another. It won 36% of sessions asked as junior developer and 3% of those asked as enterprise team.
| Who is asking | Sessions | Chose Vapi | Share |
|---|---|---|---|
| Vibe coder | 62 | 20 | 32% |
| Junior developer | 42 | 15 | 36% |
| Senior engineer | 128 | 37 | 29% |
| Enterprise team | 76 | 2 | 3% |
What Vapi was up against
The full ranking in voice agents, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Vapi (this page) | 74 | 24% |
| 2 | Retell AI | 55 | 18% |
| 3 | OpenAI Realtime API | 37 | 12% |
| 4 | LiveKit Agents | 35 | 11% |
| 5 | ElevenLabs Agents | 30 | 10% |
| 6 | Twilio ConversationRelay | 28 | 9% |
| 7 | Built in-house (no product adopted) | 18 | 6% |
| 8 | Azure Voice Live API | 10 | 3% |
What this means
Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.
The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.
Where these numbers come from
The 308 sessions in voice agents are part of a published set of 5,292, 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 74 of the 308 judged sessions in voice agents, a 24% install share, ranking first in its category.
Does Claude Code recommend Vapi?
In 14 of the 94 sessions in voice agents run with Claude Code, which is 15%.
Do different coding agents treat Vapi differently?
Yes, and by a wide margin. Cursor chose it in 39% of its runs and Claude Code in 15%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 51 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 179 sessions without being chosen, and chosen in 74. That is a 29% conversion from considered to chosen.
Where this comes from
Armature ran 5,292 judged sessions with Claude Code, Codex and Cursor inside 51 realistic codebases, and published every run. The numbers on this page come from that work.