From the experiment

Do coding agents recommend ALTCHA?

ALTCHA was chosen in 8% of 160 judged bot protection sessions, ranking third. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

ALTCHA was chosen in 8% of 160 judged bot protection sessions, ranking third. It was also raised as a candidate in 41 further sessions without being chosen.

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

The numbers

CategoryBot protection
Sessions in the category160
Sessions where ALTCHA was chosen12
Install share8%
Rank in category3 of 6
Codebases it won in3
Raised as a candidate, not chosen41
Chosen when considered23%
Sitealtcha.org

By agent

With 12 wins spread across three 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 ALTCHAShare
Claude Code5400%
Codex5400%
Cursor521223%

By who was asking

ALTCHA performs similarly across the four kinds of buyer, from 0% to 13%. That is unusual: the category leader changed with the persona in 14 of the 18 categories we measured.

Who is askingSessionsChose ALTCHAShare
Vibe coder61813%
Junior developer6300%
Enterprise team36411%

What ALTCHA was up against

The full ranking in bot protection, from the same sessions:

#ProductRuns wonShare
1Cloudflare Turnstile9157%
2Vercel BotID1811%
3Built in-house (no product adopted)1811%
4ALTCHA (this page)128%
5django-axes117%
6Google reCAPTCHA64%
7Laravel RateLimiter21%

What this means

This is an integration problem, not a presence problem. Agents raised ALTCHA in 41 sessions and chose it in 12, 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 160 sessions in bot protection are part of a published set of 5,292, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every bot protection run can be replayed on the board.

If you work on ALTCHA: 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 ALTCHA?

Yes. ALTCHA was chosen in 12 of the 160 judged sessions in bot protection, a 8% install share, ranking third in its category.

Does Claude Code recommend ALTCHA?

In 0 of the 54 sessions in bot protection run with Claude Code, which is 0%.

Do different coding agents treat ALTCHA differently?

Yes, and by a wide margin. Cursor chose it in 23% of its runs and Claude Code in 0%.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 51 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 ALTCHA considered but not chosen?

It was raised as a candidate in 41 sessions without being chosen, and chosen in 12. That is a 23% conversion from considered to chosen.

Where this comes from

Armature ran 5,292 judged sessions with Claude Code, Codex and Cursor inside 51 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages