From the experiment

Do coding agents recommend Oracle Indexed Search?

Oracle Indexed Search was chosen in 5% of 459 judged search sessions, ranking fifth. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Oracle Indexed Search was chosen in 5% of 459 judged search sessions, ranking fifth.

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

One thing to read first: every one of those wins came from a single codebase. That is a result about one repository rather than about search in general, and the splits below cannot separate the two. Treat them as a description of that repository.

The numbers

CategorySearch
Sessions in the category459
Sessions where Oracle Indexed Search was chosen23
Install share5%
Rank in category5 of 16
Codebases it won in1
Raised as a candidate, not chosen0
Chosen when considered100%
Siteoracle.com

By agent

The three agents agree closely on Oracle Indexed Search, choosing it at rates within 2 points of each other.

AgentSessionsChose Oracle Indexed SearchShare
Claude Code15285%
Codex15564%
Cursor15296%

By who was asking

Oracle Indexed Search does much better with one kind of buyer than another. It won 15% of sessions asked as enterprise team and 0% of those asked as senior engineer.

Who is askingSessionsChose Oracle Indexed SearchShare
Vibe coder6500%
Junior developer19395%
Senior engineer10600%
Enterprise team951415%

What Oracle Indexed Search was up against

The full ranking in search, from the same sessions:

#ProductRuns wonShare
1Built in-house (no product adopted)10623%
2Postgres Full-Text Search7917%
3OpenSearch5913%
4Typesense429%
5Meilisearch409%
6Oracle Indexed Search (this page)235%
7Algolia235%
8Elasticsearch225%

What this means

Agents almost never raise Oracle Indexed Search without choosing it: 0 sessions raised against 23 chosen. When it gets considered, it usually wins. The constraint is how rarely it gets considered at all, which is a presence problem: templates, framework integrations and pages that answer the configuration and production questions agents actually search for.

Where these numbers come from

The 459 sessions in search 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 search run can be replayed on the board.

If you work on Oracle Indexed Search: 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 Oracle Indexed Search?

Yes. Oracle Indexed Search was chosen in 23 of the 459 judged sessions in search, a 5% install share, ranking fifth in its category.

Does Claude Code recommend Oracle Indexed Search?

In 8 of the 152 sessions in search run with Claude Code, which is 5%.

Do different coding agents treat Oracle Indexed Search differently?

Not much. The three agents chose it at similar rates, between 4% and 6% of their runs.

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.

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