From the experiment

Do coding agents recommend Lokalise?

Coding agents raised Lokalise in 120 of 224 judged internationalization sessions and chose it in none of them. Measured with Claude Code, Codex and Cursor.

Published September 11, 2026 Read as Markdown

Coding agents raised Lokalise in 120 of 224 judged internationalization sessions and chose it in none of them.

This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in internationalization inside a realistic codebase. Not what a chat assistant says about Lokalise. What an agent actually installed.

The numbers

CategoryInternationalization
Sessions in the category224
Sessions where Lokalise was chosen0
Install share0%
Raised as a candidate, not chosen120
Chosen when considered0%
Sitelokalise.com

Which agents raised Lokalise

Every agent considered it and none adopted it. Claude Code raised it most often, in 70% of its internationalization sessions.

AgentSessionsRaised LokaliseChose it
Claude Code7754 (70%)0
Codex7818 (23%)0
Cursor6948 (70%)0

Which buyers it came up for

It surfaced most for requests written as enterprise team, in 67% of those sessions. Knowing which buyer already has the product in mind tells you which pages to fix first.

Who is askingSessionsRaised it
Vibe coder5423 (43%)
Junior developer6934 (49%)
Senior engineer4727 (57%)
Enterprise team5436 (67%)

What Lokalise was up against

The full ranking in internationalization, from the same sessions:

#ProductRuns wonShare
1next-intl5725%
2Django translation framework4520%
3Symfony Translation188%
4Paraglide JS188%
5Rails I18n178%
6i18next146%
7Built in-house (no product adopted)125%
8Vue I18n104%

What this means

Raised 120 times and chosen none is a specific, diagnosable result, and a better starting position than being unknown. The agent has the product in mind. It reached the shortlist 120 times. Something then lost every one of those sessions.

In our data the causes, in the order they occur:

  • The quickstart does not run when pasted, so the agent abandoned it mid-integration.
  • The documentation describes an interface that changed, so the generated code failed.
  • The product name and the package name differ, so the install step went wrong.
  • The fit was genuinely wrong for the repository, which is fine and worth knowing.

All but the last are fixable in days, and the reason is written down in the session transcript.

Where these numbers come from

The 224 sessions in internationalization are part of a published set of 6,458, 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 Lokalise: 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 Lokalise?

They raise it but do not choose it. Across 120 sessions where Lokalise came up as a candidate, agents chose something else every time.

Does Claude Code recommend Lokalise?

In 0 of the 77 sessions in internationalization run with Claude Code, which is 0%.

Do different coding agents treat Lokalise differently?

Not much. The three agents chose it at similar rates, between 0% and 0% of their runs.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 63 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 6,458 judged sessions with Claude Code, Codex and Cursor inside 63 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages