Do coding agents recommend Cloudflare R2?
Cloudflare R2 was chosen in 12% of 281 judged file storage sessions, ranking fourth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Cloudflare R2 was chosen in 12% of 281 judged file storage sessions, ranking fourth. It was also raised as a candidate in 105 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 file storage inside a realistic codebase. Not what a chat assistant says about Cloudflare R2. What an agent actually installed.
The numbers
| Category | File storage |
| Sessions in the category | 281 |
| Sessions where Cloudflare R2 was chosen | 35 |
| Install share | 12% |
| Rank in category | 4 of 6 |
| Codebases it won in | 4 |
| Raised as a candidate, not chosen | 105 |
| Chosen when considered | 25% |
| Site | cloudflare.com |
By agent
The agents treat Cloudflare R2 very differently. Claude Code chose it in 22% of its sessions in this category and Muse Code in 6%, a spread of 16 points. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose Cloudflare R2 | Share |
|---|---|---|---|
| Claude Code | 54 | 12 | 22% |
| Codex | 78 | 9 | 12% |
| Cursor | 54 | 7 | 13% |
| Grok Build CLI | 23 | 3 | 13% |
| Muse Code | 72 | 4 | 6% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Muse Code, your real position here is 6%, not 12%.
By who was asking
Cloudflare R2 does much better with one kind of buyer than another. It won 22% of sessions asked as senior engineer and 0% of those asked as enterprise team.
| Who is asking | Sessions | Chose Cloudflare R2 | Share |
|---|---|---|---|
| Vibe coder | 32 | 0 | 0% |
| Junior developer | 66 | 13 | 20% |
| Senior engineer | 99 | 22 | 22% |
| Enterprise team | 84 | 0 | 0% |
What Cloudflare R2 was up against
The full ranking in file storage, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Amazon S3 | 150 | 53% |
| 2 | Azure Blob Storage | 42 | 15% |
| 3 | Google Cloud Storage | 42 | 15% |
| 4 | Cloudflare R2 (this page) | 35 | 12% |
| 5 | Built in-house (no product adopted) | 8 | 3% |
| 6 | Tigris | 2 | 1% |
| 7 | MinIO | 2 | 1% |
What this means
This is an integration problem, not a presence problem. Agents raised Cloudflare R2 in 105 sessions and chose it in 35, 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 281 sessions in file storage 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 file storage run can be replayed on the board.
If you work on Cloudflare R2: 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 Cloudflare R2?
Yes. Cloudflare R2 was chosen in 35 of the 281 judged sessions in file storage, a 12% install share, ranking fourth in its category.
Does Claude Code recommend Cloudflare R2?
In 12 of the 54 sessions in file storage run with Claude Code, which is 22%.
Do different coding agents treat Cloudflare R2 differently?
Yes, and by a wide margin. Claude Code chose it in 22% of its runs and Muse Code in 6%.
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 Cloudflare R2 considered but not chosen?
It was raised as a candidate in 105 sessions without being chosen, and chosen in 35. That is a 25% 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.