From the experiment

Do coding agents recommend Smallest AI Voice Agents?

Smallest AI Voice Agents was chosen in 1% of 621 judged voice agents sessions, ranking tenth.

Published September 24, 2026 Read as Markdown

Smallest AI Voice Agents was chosen in 1% of 621 judged voice agents sessions, ranking tenth.

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 Smallest AI Voice Agents. What an agent actually installed.

The numbers

CategoryVoice agents
Sessions in the category621
Sessions where Smallest AI Voice Agents was chosen9
Install share1%
Rank in category10 of 31
Codebases it won in3
Raised as a candidate, not chosen0
Chosen when considered100%
Sitesmallest.ai

By agent

With 9 wins spread across 5 agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.

AgentSessionsChose Smallest AI Voice AgentsShare
Claude Code13900%
Codex15532%
Cursor14900%
Grok Build CLI4300%
Muse Code13564%

By who was asking

Smallest AI Voice Agents performs similarly across the four kinds of buyer, from 0% to 2%. That is unusual: the category leader changed with the persona in 22 of the 29 categories we measured.

Who is askingSessionsChose Smallest AI Voice AgentsShare
Vibe coder12511%
Junior developer8400%
Senior engineer25952%
Enterprise team15332%

What Smallest AI Voice Agents was up against

The full ranking in voice agents, from the same sessions:

#ProductRuns wonShare
1Retell AI13822%
2Vapi11318%
3LiveKit Agents8013%
4Twilio ConversationRelay589%
5ElevenLabs Agents559%
6OpenAI Realtime API467%
7Built in-house (no product adopted)345%
8Azure Voice Live API173%

What this means

Agents almost never raise Smallest AI Voice Agents without choosing it: 0 sessions raised against 9 chosen. When it gets considered, it usually wins. The constraint is how rarely it gets considered at all, which is a presence problem: templates, framework integrations and pages that answer the configuration and production questions agents actually search for.

Where these numbers come from

The 621 sessions in voice agents are part of a published set of 13,497, 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 Smallest AI Voice 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 Smallest AI Voice Agents?

Yes. Smallest AI Voice Agents was chosen in 9 of the 621 judged sessions in voice agents, a 1% install share, ranking tenth in its category.

Does Claude Code recommend Smallest AI Voice Agents?

In 0 of the 139 sessions in voice agents run with Claude Code, which is 0%.

Do different coding agents treat Smallest AI Voice Agents differently?

Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 4% of their runs.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 91 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.

Where this comes from

Armature ran 13,497 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 91 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages