Do coding agents recommend Elasticsearch?
Elasticsearch was chosen in 5% of 876 judged search sessions, ranking seventh. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Elasticsearch was chosen in 5% of 876 judged search sessions, ranking seventh. It was also raised as a candidate in 545 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 search inside a realistic codebase. Not what a chat assistant says about Elasticsearch. What an agent actually installed.
The numbers
| Category | Search |
| Sessions in the category | 876 |
| Sessions where Elasticsearch was chosen | 42 |
| Install share | 5% |
| Rank in category | 7 of 18 |
| Codebases it won in | 5 |
| Raised as a candidate, not chosen | 545 |
| Chosen when considered | 7% |
| Site | elastic.co |
By agent
Claude Code, Codex, Cursor, Grok Build CLI and Muse Code agree closely on Elasticsearch, choosing it at rates within 4 points of each other.
| Agent | Sessions | Chose Elasticsearch | Share |
|---|---|---|---|
| Claude Code | 205 | 4 | 2% |
| Codex | 261 | 16 | 6% |
| Cursor | 199 | 12 | 6% |
| Grok Build CLI | 53 | 1 | 2% |
| Muse Code | 158 | 9 | 6% |
By who was asking
Elasticsearch performs similarly across the four kinds of buyer, from 0% to 13%. That is unusual: the category leader changed with the persona in 24 of the 31 categories we measured.
| Who is asking | Sessions | Chose Elasticsearch | Share |
|---|---|---|---|
| Vibe coder | 127 | 0 | 0% |
| Junior developer | 296 | 1 | 0% |
| Senior engineer | 201 | 27 | 13% |
| Enterprise team | 252 | 14 | 6% |
What Elasticsearch was up against
The full ranking in search, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Built in-house (no product adopted) | 208 | 24% |
| 2 | Postgres Full-Text Search | 140 | 16% |
| 3 | OpenSearch | 104 | 12% |
| 4 | Typesense | 83 | 9% |
| 5 | Meilisearch | 74 | 8% |
| 6 | Oracle Indexed Search | 46 | 5% |
| 7 | Algolia | 45 | 5% |
| 8 | Elasticsearch (this page) | 42 | 5% |
What this means
This is an integration problem, not a presence problem. Agents raised Elasticsearch in 545 sessions and chose it in 42, 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 876 sessions in search are part of a published set of 15,287, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every search run can be replayed on the board.
If you work on Elasticsearch: 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 Elasticsearch?
Yes. Elasticsearch was chosen in 42 of the 876 judged sessions in search, a 5% install share, ranking seventh in its category.
Does Claude Code recommend Elasticsearch?
In 4 of the 205 sessions in search run with Claude Code, which is 2%.
Do different coding agents treat Elasticsearch differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 2% and 6% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 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 Elasticsearch considered but not chosen?
It was raised as a candidate in 545 sessions without being chosen, and chosen in 42. That is a 7% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.