Do coding agents recommend Spring AI?
Spring AI was chosen in 2% of 681 judged agent frameworks sessions, ranking number 12. Measured with Claude Code, Codex and Cursor.
Spring AI was chosen in 2% of 681 judged agent frameworks sessions, ranking number 12. It was also raised as a candidate in 11 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in agent frameworks inside a realistic codebase. Not what a chat assistant says about Spring AI. 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 agent frameworks in general, and the splits below cannot separate the two. Treat them as a description of that repository.
The numbers
| Category | Agent frameworks |
| Sessions in the category | 681 |
| Sessions where Spring AI was chosen | 11 |
| Install share | 2% |
| Rank in category | 12 of 35 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 11 |
| Chosen when considered | 50% |
| Site | spring.io |
By agent
With 11 wins spread across three 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 Spring AI | Share |
|---|---|---|---|
| Claude Code | 237 | 3 | 1% |
| Codex | 243 | 4 | 2% |
| Cursor | 201 | 4 | 2% |
By who was asking
Spring AI performs similarly across the four kinds of buyer, from 0% to 10%. That is unusual: the category leader changed with the persona in 14 of the 18 categories we measured.
| Who is asking | Sessions | Chose Spring AI | Share |
|---|---|---|---|
| Vibe coder | 163 | 0 | 0% |
| Junior developer | 157 | 0 | 0% |
| Senior engineer | 254 | 0 | 0% |
| Enterprise team | 107 | 11 | 10% |
What Spring AI was up against
The full ranking in agent frameworks, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Built in-house (no product adopted) | 170 | 25% |
| 2 | Vercel AI SDK | 95 | 14% |
| 3 | Cursor SDK | 94 | 14% |
| 4 | Inngest | 50 | 7% |
| 5 | Temporal | 29 | 4% |
| 6 | Prism | 28 | 4% |
| 7 | OpenAI Agents SDK | 24 | 4% |
| 8 | LangGraph | 23 | 3% |
What this means
Spring AI was raised in 11 sessions and chosen in 11. 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 681 sessions in agent frameworks 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 agent frameworks run can be replayed on the board.
If you work on Spring AI: 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 Spring AI?
Yes. Spring AI was chosen in 11 of the 681 judged sessions in agent frameworks, a 2% install share, ranking number 12 in its category.
Does Claude Code recommend Spring AI?
In 3 of the 237 sessions in agent frameworks run with Claude Code, which is 1%.
Do different coding agents treat Spring AI differently?
Not much. The three agents chose it at similar rates, between 1% and 2% 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 Spring AI considered but not chosen?
It was raised as a candidate in 11 sessions without being chosen, and chosen in 11. That is a 50% 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.