From the experiment

Do coding agents recommend Apache Kafka?

Apache Kafka is the most chosen message queue, taking 14% of 288 judged message queues sessions. Measured with Claude Code, Codex and Cursor.

Published September 15, 2026 Read as Markdown

Apache Kafka is the most chosen message queue, taking 14% of 288 judged message queues sessions. It was also raised as a candidate in 136 further sessions without being chosen.

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

The numbers

CategoryMessage queues
Sessions in the category288
Sessions where Apache Kafka was chosen39
Install share14%
Rank in category1 of 25
Codebases it won in2
Raised as a candidate, not chosen136
Chosen when considered22%
Sitekafka.apache.org

By agent

The three agents agree closely on Apache Kafka, choosing it at rates within 5 points of each other.

AgentSessionsChose Apache KafkaShare
Claude Code961516%
Codex961111%
Cursor961314%

By who was asking

Apache Kafka does much better with one kind of buyer than another. It won 22% of sessions asked as enterprise team and 0% of those asked as senior engineer.

Who is askingSessionsChose Apache KafkaShare
Vibe coder4800%
Junior developer1202319%
Senior engineer4800%
Enterprise team721622%

What Apache Kafka was up against

The full ranking in message queues, from the same sessions:

#ProductRuns wonShare
1Built in-house (no product adopted)4917%
2Apache Kafka (this page)3914%
3Amazon SQS279%
4Service Bus248%
5Laravel Queues207%
6Amazon Kinesis197%
7Cloudflare Queues197%
8Cloud Tasks155%

What this means

Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.

The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.

Where these numbers come from

The 288 sessions in message queues are part of a published set of 7,852, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every message queues run can be replayed on the board.

If you work on Apache Kafka: 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 Apache Kafka?

Yes. Apache Kafka was chosen in 39 of the 288 judged sessions in message queues, a 14% install share, ranking first in its category.

Does Claude Code recommend Apache Kafka?

In 15 of the 96 sessions in message queues run with Claude Code, which is 16%.

Do different coding agents treat Apache Kafka differently?

Not much. The three agents chose it at similar rates, between 11% and 16% of their runs.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 90 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 Apache Kafka considered but not chosen?

It was raised as a candidate in 136 sessions without being chosen, and chosen in 39. That is a 22% conversion from considered to chosen.

Where this comes from

Armature ran 7,852 judged sessions with Claude Code, Codex and Cursor inside 90 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages