From the experiment

Do coding agents recommend Perigon?

Perigon was chosen in 2% of 499 judged AI search sessions, ranking number 12. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.

Published September 23, 2026 Read as Markdown

Perigon was chosen in 2% of 499 judged AI search sessions, ranking number 12. It was also raised as a candidate in 17 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 AI search inside a realistic codebase. Not what a chat assistant says about Perigon. What an agent actually installed.

The numbers

CategoryAI search
Sessions in the category499
Sessions where Perigon was chosen8
Install share2%
Rank in category12 of 41
Codebases it won in2
Raised as a candidate, not chosen17
Chosen when considered32%
Siteperigon.io

By agent

With 8 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 PerigonShare
Claude Code14043%
Codex14400%
Cursor13621%
Grok Build CLI3526%
Muse Code4400%

By who was asking

Perigon performs similarly across the four kinds of buyer, from 0% to 6%. That is unusual: the category leader changed with the persona in 23 of the 29 categories we measured.

Who is askingSessionsChose PerigonShare
Vibe coder8200%
Junior developer17300%
Senior engineer12411%
Enterprise team12076%

What Perigon was up against

The full ranking in AI search, from the same sessions:

#ProductRuns wonShare
1Anthropic web search8417%
2Brave Search API6914%
3Exa6713%
4Tavily428%
5OpenAI web search275%
6Built in-house (no product adopted)245%
7Firecrawl235%
8NewsAPI.ai235%

What this means

Perigon was raised in 17 sessions and chosen in 8. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.

Where these numbers come from

The 499 sessions in AI search are part of a published set of 11,878, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every AI search run can be replayed on the board.

If you work on Perigon: 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 Perigon?

Yes. Perigon was chosen in 8 of the 499 judged sessions in AI search, a 2% install share, ranking number 12 in its category.

Does Claude Code recommend Perigon?

In 4 of the 140 sessions in AI search run with Claude Code, which is 3%.

Do different coding agents treat Perigon differently?

Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 6% 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.

How often is Perigon considered but not chosen?

It was raised as a candidate in 17 sessions without being chosen, and chosen in 8. That is a 32% conversion from considered to chosen.

Where this comes from

Armature ran 11,878 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