From the experiment

Do coding agents recommend SQLite FTS?

SQLite FTS was chosen in 1% of 823 judged search sessions, ranking number 12. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.

Published September 24, 2026 Read as Markdown

SQLite FTS was chosen in 1% of 823 judged search sessions, ranking number 12. It was also raised as a candidate in 20 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 SQLite FTS. What an agent actually installed.

The numbers

CategorySearch
Sessions in the category823
Sessions where SQLite FTS was chosen8
Install share1%
Rank in category12 of 18
Codebases it won in2
Raised as a candidate, not chosen20
Chosen when considered29%
Sitesqlite.org

By agent

With 8 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.

AgentSessionsChose SQLite FTSShare
Claude Code20510%
Codex20800%
Cursor19921%
Grok Build CLI5300%
Muse Code15853%

By who was asking

SQLite FTS performs similarly across the four kinds of buyer, from 0% to 5%. That is unusual: the category leader changed with the persona in 22 of the 29 categories we measured.

Who is askingSessionsChose SQLite FTSShare
Vibe coder11965%
Junior developer28321%
Senior engineer18900%
Enterprise team23200%

What SQLite FTS was up against

The full ranking in search, from the same sessions:

#ProductRuns wonShare
1Built in-house (no product adopted)19724%
2Postgres Full-Text Search13116%
3OpenSearch9712%
4Typesense779%
5Meilisearch719%
6Oracle Indexed Search445%
7Algolia425%
8Elasticsearch385%

What this means

SQLite FTS was raised in 20 sessions and chosen in 8. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.

Where these numbers come from

The 823 sessions in search are part of a published set of 13,497, 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 SQLite FTS: 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 SQLite FTS?

Yes. SQLite FTS was chosen in 8 of the 823 judged sessions in search, a 1% install share, ranking number 12 in its category.

Does Claude Code recommend SQLite FTS?

In 1 of the 205 sessions in search run with Claude Code, which is 0%.

Do different coding agents treat SQLite FTS differently?

Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 3% of their runs.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 91 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 SQLite FTS considered but not chosen?

It was raised as a candidate in 20 sessions without being chosen, and chosen in 8. That is a 29% conversion from considered to chosen.

Where this comes from

Armature ran 13,497 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 91 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages