Do coding agents recommend Typesense?
Typesense was chosen in 9% of 459 judged search sessions, ranking third. Measured with Claude Code, Codex and Cursor.
Typesense was chosen in 9% of 459 judged search sessions, ranking third. It was also raised as a candidate in 218 further sessions without being chosen.
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 Typesense. What an agent actually installed.
The numbers
| Category | Search |
| Sessions in the category | 459 |
| Sessions where Typesense was chosen | 42 |
| Install share | 9% |
| Rank in category | 3 of 16 |
| Codebases it won in | 9 |
| Raised as a candidate, not chosen | 218 |
| Chosen when considered | 16% |
| Site | typesense.org |
By agent
The three agents land within 9 points of each other on Typesense, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose Typesense | Share |
|---|---|---|---|
| Claude Code | 152 | 18 | 12% |
| Codex | 155 | 19 | 12% |
| Cursor | 152 | 5 | 3% |
By who was asking
Typesense does much better with one kind of buyer than another. It won 20% of sessions asked as senior engineer and 0% of those asked as vibe coder.
| Who is asking | Sessions | Chose Typesense | Share |
|---|---|---|---|
| Vibe coder | 65 | 0 | 0% |
| Junior developer | 193 | 15 | 8% |
| Senior engineer | 106 | 21 | 20% |
| Enterprise team | 95 | 6 | 6% |
What Typesense was up against
The full ranking in search, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Built in-house (no product adopted) | 106 | 23% |
| 2 | Postgres Full-Text Search | 79 | 17% |
| 3 | OpenSearch | 59 | 13% |
| 4 | Typesense (this page) | 42 | 9% |
| 5 | Meilisearch | 40 | 9% |
| 6 | Oracle Indexed Search | 23 | 5% |
| 7 | Algolia | 23 | 5% |
| 8 | Elasticsearch | 22 | 5% |
What this means
This is an integration problem, not a presence problem. Agents raised Typesense in 218 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 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 Typesense: 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 Typesense?
Yes. Typesense was chosen in 42 of the 459 judged sessions in search, a 9% install share, ranking third in its category.
Does Claude Code recommend Typesense?
In 18 of the 152 sessions in search run with Claude Code, which is 12%.
Do different coding agents treat Typesense differently?
Not much. The three agents chose it at similar rates, between 3% and 12% 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.
How often is Typesense considered but not chosen?
It was raised as a candidate in 218 sessions without being chosen, and chosen in 42. That is a 16% 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.