From the experiment

Do coding agents recommend Tolgee?

Tolgee was chosen in 2% of 392 judged internationalization sessions, ranking ninth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.

Published September 23, 2026 Read as Markdown

Tolgee was chosen in 2% of 392 judged internationalization sessions, ranking ninth. It was also raised as a candidate in 61 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 internationalization inside a realistic codebase. Not what a chat assistant says about Tolgee. What an agent actually installed.

The numbers

CategoryInternationalization
Sessions in the category392
Sessions where Tolgee was chosen8
Install share2%
Rank in category9 of 28
Codebases it won in2
Raised as a candidate, not chosen61
Chosen when considered12%
Sitetolgee.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 TolgeeShare
Claude Code11311%
Codex11444%
Cursor10333%
Grok Build CLI2600%
Muse Code3600%

By who was asking

Tolgee performs similarly across the four kinds of buyer, from 0% to 7%. That is unusual: the category leader changed with the persona in 23 of the 29 categories we measured.

Who is askingSessionsChose TolgeeShare
Vibe coder8400%
Junior developer9777%
Senior engineer8611%
Enterprise team12500%

What Tolgee was up against

The full ranking in internationalization, from the same sessions:

#ProductRuns wonShare
1next-intl9223%
2Django translation framework7820%
3Symfony Translation328%
4Paraglide JS328%
5Rails I18n308%
6Built in-house (no product adopted)267%
7i18next226%
8Vue I18n205%

What this means

This is an integration problem, not a presence problem. Agents raised Tolgee in 61 sessions and chose it in 8, 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 392 sessions in internationalization 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 internationalization run can be replayed on the board.

If you work on Tolgee: 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 Tolgee?

Yes. Tolgee was chosen in 8 of the 392 judged sessions in internationalization, a 2% install share, ranking ninth in its category.

Does Claude Code recommend Tolgee?

In 1 of the 113 sessions in internationalization run with Claude Code, which is 1%.

Do different coding agents treat Tolgee differently?

Not much. Claude Code, Codex, Cursor 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.

How often is Tolgee considered but not chosen?

It was raised as a candidate in 61 sessions without being chosen, and chosen in 8. That is a 12% 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