How to get picked for file storage by coding agents
Amazon S3 took 53% of 281 judged file storage sessions. What the numbers say a vendor in this category should do.
If you sell file storage services, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for file storage and never compares vendors.
The numbers come from 281 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code, spread across 8 realistic codebases, with every session read by a judge.
What coding agents choose for file storage
Across 281 judged sessions, Amazon S3 was chosen most often, in 53% of runs. Azure Blob Storage was second with 15%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Amazon S3 | 150 | 53% |
| 2 | Azure Blob Storage | 42 | 15% |
| 3 | Google Cloud Storage | 42 | 15% |
| 4 | Cloudflare R2 | 35 | 12% |
| 5 | Built in-house (no product adopted) | 8 | 3% |
| 6 | Tigris | 2 | 1% |
| 7 | MinIO | 2 | 1% |
Full board, every run replayable: the file storage leaderboard.
What the shape of this category means
The leader takes 53% of runs and there is a real second place. The category has a default but it is not settled.
Amazon S3 at 53% with Azure Blob Storage at 15% is a default with a real challenger behind it. The agent is choosing rather than reaching, which means the inputs it uses can move the answer.
The work is to be the easiest correct answer: a quickstart that runs when pasted, documentation that states the current version, and pages that answer the exact configuration questions agents search for.
The agents do not agree with each other
In this category Claude Code, Codex and Cursor all put Amazon S3 first, which is less common than it sounds: across the 31 categories we measured, Claude Code and Codex disagreed on the leader in 16 of them.
Grok Build CLI (23 sessions) and Muse Code (72 sessions) join this table with fewer runs, so read their rows as indicative.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 54 | Amazon S3 (24) |
| Codex | 78 | Amazon S3 (44) |
| Cursor | 54 | Amazon S3 (28) |
| Grok Build CLI | 23 | Amazon S3 (14) |
| Muse Code | 72 | Amazon S3 (40) |
Even where they agree, they get there differently. In this category Codex ran a web search in 99% of its sessions and Claude Code in 6%, so what you publish reaches nearly all of Codex's file storage sessions and almost none of Claude Code's.
Who is asking changes the answer
Every request in this experiment was written as a specific kind of person. In this category the leader changes with the person.
| Who is asking | Runs | Picked most often |
|---|---|---|
| Vibe coder | 32 | Amazon S3 |
| Junior developer | 66 | Amazon S3 |
| Senior engineer | 99 | Amazon S3 |
| Enterprise team | 84 | Azure Blob Storage |
That is 2 different products winning file storage for 4 kinds of buyer, out of the same 281 sessions. Nobody here is winning file storage. They are each winning one kind of buyer.
If you sell to more than one of them, you need pages for each. See how to win the enterprise persona.
What you are really competing against
In 3% of runs the agent wrote the code itself rather than adopting a product. That is low enough that your competition is other vendors, but high enough to be worth watching.
Considered, and never chosen
Because the judge records every product an agent raised and not only the one it picked, this board also shows who kept reaching the shortlist and losing. In file storage the clearest case is Supabase Storage: on the table in 28 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Supabase Storage | 28 sessions | 0 |
| Backblaze B2 | 26 sessions | 0 |
| DigitalOcean Spaces | 26 sessions | 0 |
| Azure Files | 24 sessions | 0 |
Being rejected is a better position than being unknown, and a cheaper one to fix. The product is already in the agent's head and on the list. Whatever ended those 104 sessions is recorded in each transcript, one reason at a time.
What to do about it in file storage
- Aim at second place first. Amazon S3 holds 53% and Azure Blob Storage holds 15%. The gap between the default and the field is where the reachable sessions are.
- Pick which buyer you are for. The same file storage need written as a vibe coder landed on Amazon S3, and written as an enterprise team landed on Azure Blob Storage. Those are two markets, and the enterprise one needs pages containing the constraint words: audit log, data residency, retention, single sign-on. See how to win the enterprise persona.
The work that applies to every category rather than to this one is written up separately: audit your documentation, write a quickstart an agent can follow, and how to measure install share.
Every file storage service on this board
One page per product, with its install share, the per-agent split, and how often it was raised without being chosen.
- Do coding agents recommend Amazon S3? — chosen in 53% of sessions
- Do coding agents recommend Azure Blob Storage? — chosen in 15% of sessions
- Do coding agents recommend Google Cloud Storage? — chosen in 15% of sessions
- Do coding agents recommend Cloudflare R2? — chosen in 12% of sessions
- Do coding agents recommend MinIO? — chosen in 1% of sessions
Where these numbers come from
281 judged sessions in file storage across 8 codebases, part of a published set of 15,287. Real coding agents at pinned versions, in sandboxes, inside realistic codebases, with a simulated project owner in the loop and a blind judge on every session. The full method is on one page: how we measured this.
Every file storage run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
281 judged sessions across 8 realistic codebases. A category only runs on repositories where its seam is open, so coverage differs: some categories ran on more than ten codebases and some on two.
What file storage service do coding agents choose?
Across 281 judged sessions, Amazon S3 was chosen most often, in 53% of runs. Azure Blob Storage was second with 15%. The result changes by who is asking.
Do Claude Code and Codex pick the same file storage service?
Yes. Claude Code and Codex both put Amazon S3 first in this category, which is less common than it sounds: they disagree on the leader in 16 of the 31 categories we measured.
How often do agents build file storage themselves instead of installing something?
In 3% of runs the agent wrote the code itself rather than adopting a product.
How can a vendor improve its position here?
Make the quickstart run when pasted, state the current version on the documentation page, use one name across product, package and import, write pages for the symptoms users describe rather than only the category name, and get into the repository through templates and framework integrations.
Which file storage services do agents consider but never choose?
Supabase Storage (raised in 28 sessions, chosen in none), Backblaze B2 (raised in 26 sessions, chosen in none), DigitalOcean Spaces (raised in 26 sessions, chosen in none), Azure Files (raised in 24 sessions, chosen in none). Being considered and not chosen is a different problem from being unknown, and it is usually fixable.
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.