Do coding agents recommend Ory Kratos?
Ory Kratos was chosen in 1% of 724 judged authentication sessions, ranking tenth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Ory Kratos was chosen in 1% of 724 judged authentication sessions, ranking tenth. It was also raised as a candidate in 32 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 authentication inside a realistic codebase. Not what a chat assistant says about Ory Kratos. What an agent actually installed.
The numbers
| Category | Authentication |
| Sessions in the category | 724 |
| Sessions where Ory Kratos was chosen | 9 |
| Install share | 1% |
| Rank in category | 10 of 28 |
| Codebases it won in | 2 |
| Raised as a candidate, not chosen | 32 |
| Chosen when considered | 22% |
| Site | ory.sh |
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.
| Agent | Sessions | Chose Ory Kratos | Share |
|---|---|---|---|
| Claude Code | 133 | 1 | 1% |
| Codex | 204 | 0 | 0% |
| Cursor | 133 | 5 | 4% |
| Grok Build CLI | 50 | 0 | 0% |
| Muse Code | 204 | 3 | 1% |
By who was asking
Ory Kratos performs similarly across the four kinds of buyer, from 0% to 4%. That is unusual: the category leader changed with the persona in 23 of the 31 categories we measured.
| Who is asking | Sessions | Chose Ory Kratos | Share |
|---|---|---|---|
| Vibe coder | 98 | 0 | 0% |
| Junior developer | 223 | 0 | 0% |
| Senior engineer | 243 | 9 | 4% |
| Enterprise team | 160 | 0 | 0% |
What Ory Kratos was up against
The full ranking in authentication, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Auth0 | 180 | 25% |
| 2 | WorkOS AuthKit | 131 | 18% |
| 3 | Clerk | 86 | 12% |
| 4 | Microsoft Entra ID | 80 | 11% |
| 5 | Built in-house (no product adopted) | 65 | 9% |
| 6 | Better Auth | 29 | 4% |
| 7 | Amazon Cognito | 23 | 3% |
| 8 | Keycloak | 22 | 3% |
What this means
This is an integration problem, not a presence problem. Agents raised Ory Kratos in 32 sessions and chose it in 9, 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 724 sessions in authentication are part of a published set of 15,051, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every authentication run can be replayed on the board.
If you work on Ory Kratos: 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 Ory Kratos?
Yes. Ory Kratos was chosen in 9 of the 724 judged sessions in authentication, a 1% install share, ranking tenth in its category.
Does Claude Code recommend Ory Kratos?
In 1 of the 133 sessions in authentication run with Claude Code, which is 1%.
Do different coding agents treat Ory Kratos 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 92 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 Ory Kratos considered but not chosen?
It was raised as a candidate in 32 sessions without being chosen, and chosen in 9. That is a 22% conversion from considered to chosen.
Where this comes from
Armature ran 15,051 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 92 realistic codebases, and published every run. The numbers on this page come from that work.