Do coding agents recommend Retell AI?
Retell AI is the most chosen voice agent platform, taking 22% of 754 judged voice agents sessions.
Retell AI is the most chosen voice agent platform, taking 22% of 754 judged voice agents sessions. It was also raised as a candidate in 200 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 Retell AI. What an agent actually installed.
The numbers
| Category | Voice agents |
| Sessions in the category | 754 |
| Sessions where Retell AI was chosen | 168 |
| Install share | 22% |
| Rank in category | 1 of 32 |
| Codebases it won in | 10 |
| Raised as a candidate, not chosen | 200 |
| Chosen when considered | 46% |
| Site | retellai.com |
By agent
Claude Code, Codex, Cursor, Grok Build CLI and Muse Code land within 14 points of each other on Retell AI, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose Retell AI | Share |
|---|---|---|---|
| Claude Code | 157 | 25 | 16% |
| Codex | 217 | 64 | 29% |
| Cursor | 167 | 29 | 17% |
| Grok Build CLI | 60 | 9 | 15% |
| Muse Code | 153 | 41 | 27% |
By who was asking
Retell AI does much better with one kind of buyer than another. It won 50% of sessions asked as vibe coder and 6% of those asked as enterprise team.
| Who is asking | Sessions | Chose Retell AI | Share |
|---|---|---|---|
| Vibe coder | 134 | 67 | 50% |
| Junior developer | 90 | 22 | 24% |
| Senior engineer | 322 | 67 | 21% |
| Enterprise team | 208 | 12 | 6% |
What Retell AI was up against
The full ranking in voice agents, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Retell AI (this page) | 168 | 22% |
| 2 | Vapi | 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
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 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 Retell AI: 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 Retell AI?
Yes. Retell AI was chosen in 168 of the 754 judged sessions in voice agents, a 22% install share, ranking first in its category.
Does Claude Code recommend Retell AI?
In 25 of the 157 sessions in voice agents run with Claude Code, which is 16%.
Do different coding agents treat Retell AI differently?
Yes, and by a wide margin. Codex chose it in 29% of its runs and Grok Build CLI in 15%.
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 Retell AI considered but not chosen?
It was raised as a candidate in 200 sessions without being chosen, and chosen in 168. That is a 46% 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.