Do coding agents recommend LiveKit Agents?
LiveKit Agents was chosen in 11% of 308 judged voice agents sessions, ranking fourth. Measured with Claude Code, Codex and Cursor.
LiveKit Agents was chosen in 11% of 308 judged voice agents sessions, ranking fourth. It was also raised as a candidate in 110 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 LiveKit Agents. What an agent actually installed.
The numbers
| Category | Voice agents |
| Sessions in the category | 308 |
| Sessions where LiveKit Agents was chosen | 35 |
| Install share | 11% |
| Rank in category | 4 of 18 |
| Codebases it won in | 6 |
| Raised as a candidate, not chosen | 110 |
| Chosen when considered | 24% |
| Site | livekit.io |
By agent
The three agents land within 10 points of each other on LiveKit Agents, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose LiveKit Agents | Share |
|---|---|---|---|
| Claude Code | 94 | 15 | 16% |
| Codex | 110 | 7 | 6% |
| Cursor | 104 | 13 | 13% |
By who was asking
LiveKit Agents does much better with one kind of buyer than another. It won 30% of sessions asked as enterprise team and 0% of those asked as vibe coder.
| Who is asking | Sessions | Chose LiveKit Agents | Share |
|---|---|---|---|
| Vibe coder | 62 | 0 | 0% |
| Junior developer | 42 | 2 | 5% |
| Senior engineer | 128 | 10 | 8% |
| Enterprise team | 76 | 23 | 30% |
What LiveKit Agents was up against
The full ranking in voice agents, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Vapi | 74 | 24% |
| 2 | Retell AI | 55 | 18% |
| 3 | OpenAI Realtime API | 37 | 12% |
| 4 | LiveKit Agents (this page) | 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
This is an integration problem, not a presence problem. Agents raised LiveKit Agents in 110 sessions and chose it in 35, 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 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 LiveKit Agents: 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 LiveKit Agents?
Yes. LiveKit Agents was chosen in 35 of the 308 judged sessions in voice agents, a 11% install share, ranking fourth in its category.
Does Claude Code recommend LiveKit Agents?
In 15 of the 94 sessions in voice agents run with Claude Code, which is 16%.
Do different coding agents treat LiveKit Agents differently?
Yes, and by a wide margin. Claude Code chose it in 16% of its runs and Codex in 6%.
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 LiveKit Agents considered but not chosen?
It was raised as a candidate in 110 sessions without being chosen, and chosen in 35. That is a 24% 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.