Do coding agents recommend Supabase?
Supabase was chosen in 3% of 496 judged databases sessions, ranking fifth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Supabase was chosen in 3% of 496 judged databases sessions, ranking fifth. It was also raised as a candidate in 281 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 databases inside a realistic codebase. Not what a chat assistant says about Supabase. What an agent actually installed.
The numbers
| Category | Databases |
| Sessions in the category | 496 |
| Sessions where Supabase was chosen | 17 |
| Install share | 3% |
| Rank in category | 5 of 15 |
| Codebases it won in | 5 |
| Raised as a candidate, not chosen | 281 |
| Chosen when considered | 6% |
| Site | supabase.com |
By agent
With 17 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.
| Agent | Sessions | Chose Supabase | Share |
|---|---|---|---|
| Claude Code | 147 | 3 | 2% |
| Codex | 139 | 10 | 7% |
| Cursor | 142 | 1 | 1% |
| Grok Build CLI | 18 | 1 | 6% |
| Muse Code | 50 | 2 | 4% |
By who was asking
Supabase performs similarly across the four kinds of buyer, from 0% to 5%. That is unusual: the category leader changed with the persona in 23 of the 31 categories we measured.
| Who is asking | Sessions | Chose Supabase | Share |
|---|---|---|---|
| Vibe coder | 83 | 0 | 0% |
| Junior developer | 153 | 3 | 2% |
| Senior engineer | 260 | 14 | 5% |
What Supabase was up against
The full ranking in databases, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Neon | 316 | 64% |
| 2 | Azure Database for PostgreSQL Flexible Server | 45 | 9% |
| 3 | Azure SQL Database | 41 | 8% |
| 4 | Amazon RDS for PostgreSQL | 29 | 6% |
| 5 | Supabase (this page) | 17 | 3% |
| 6 | Scaleway Managed Database for PostgreSQL | 13 | 3% |
| 7 | MotherDuck | 11 | 2% |
| 8 | DigitalOcean Managed PostgreSQL | 7 | 1% |
What this means
This is an integration problem, not a presence problem. Agents raised Supabase in 281 sessions and chose it in 17, 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 496 sessions in databases are part of a published set of 15,051, 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 Supabase: 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 Supabase?
Yes. Supabase was chosen in 17 of the 496 judged sessions in databases, a 3% install share, ranking fifth in its category.
Does Claude Code recommend Supabase?
In 3 of the 147 sessions in databases run with Claude Code, which is 2%.
Do different coding agents treat Supabase differently?
Not much. Claude Code, Codex, Cursor and Muse Code chose it at similar rates, between 1% and 7% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 92 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 Supabase considered but not chosen?
It was raised as a candidate in 281 sessions without being chosen, and chosen in 17. That is a 6% conversion from considered to chosen.
Where this comes from
Armature ran 15,051 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 92 realistic codebases, and published every run. The numbers on this page come from that work.