Do coding agents recommend Turso?
Turso was chosen in 7% of 732 judged databases sessions, ranking third. Measured with Claude Code, Codex and Cursor.
Turso was chosen in 7% of 732 judged databases sessions, ranking third. It was also raised as a candidate in 234 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in databases inside a realistic codebase. Not what a chat assistant says about Turso. What an agent actually installed.
The numbers
| Category | Databases |
| Sessions in the category | 732 |
| Sessions where Turso was chosen | 48 |
| Install share | 7% |
| Rank in category | 3 of 19 |
| Codebases it won in | 10 |
| Raised as a candidate, not chosen | 234 |
| Chosen when considered | 17% |
| Site | turso.tech |
By agent
Claude Code, Codex and Cursor land within 9 points of each other on Turso, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose Turso | Share |
|---|---|---|---|
| Claude Code | 380 | 34 | 9% |
| Codex | 181 | 0 | 0% |
| Cursor | 171 | 14 | 8% |
By who was asking
Turso performs similarly across the four kinds of buyer, from 0% to 8%. That is unusual: the category leader changed with the persona in 24 of the 31 categories we measured.
| Who is asking | Sessions | Chose Turso | Share |
|---|---|---|---|
| Vibe coder | 417 | 29 | 7% |
| Junior developer | 163 | 13 | 8% |
| Senior engineer | 113 | 6 | 5% |
| Enterprise team | 24 | 0 | 0% |
What Turso was up against
The full ranking in databases, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Neon | 334 | 46% |
| 2 | Supabase | 269 | 37% |
| 3 | Turso (this page) | 48 | 7% |
| 4 | Azure Database for PostgreSQL Flexible Server | 21 | 3% |
| 5 | Firebase | 17 | 2% |
| 6 | Google Sheets | 10 | 1% |
| 7 | Netlify Forms | 6 | 1% |
| 8 | Formspree | 4 | 1% |
What this means
This is an integration problem, not a presence problem. Agents raised Turso in 234 sessions and chose it in 48, 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 732 sessions in databases 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 databases run can be replayed on the board.
If you work on Turso: 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 Turso?
Yes. Turso was chosen in 48 of the 732 judged sessions in databases, a 7% install share, ranking third in its category.
Does Claude Code recommend Turso?
In 34 of the 380 sessions in databases run with Claude Code, which is 9%.
Do different coding agents treat Turso differently?
Not much. Claude Code, Codex and Cursor chose it at similar rates, between 0% and 9% 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 Turso considered but not chosen?
It was raised as a candidate in 234 sessions without being chosen, and chosen in 48. That is a 17% 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.