Do coding agents recommend Docker?
Docker came up in 35% of judged code sandboxes sessions and was adopted in none: on this board it is substrate, not a candidate.
Docker came up in 35% of judged code sandboxes sessions and was adopted in none: on this board it is substrate, not a candidate.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in code sandboxes inside a realistic codebase. Not what a chat assistant says about Docker. What an agent actually installed.
The numbers
| Category | Code sandboxes |
| Sessions in the category | 520 |
| Sessions where Docker was chosen | 0 |
| Install share | 0% |
| Raised as a candidate, not chosen | 182 |
| Chosen when considered | 0% |
| Site | docker.com |
Which agents raised Docker
Docker came up in 35% of code sandboxes sessions and was adopted in none. At that rate it is not a candidate that keeps losing: it is the thing already in the repository, or the standard the alternatives get measured against. Cursor named it in 60% of its sessions.
| Agent | Sessions | Raised Docker | Chose it |
|---|---|---|---|
| Claude Code | 129 | 31 (24%) | 0 |
| Codex | 170 | 41 (24%) | 0 |
| Cursor | 136 | 81 (60%) | 0 |
| Grok Build CLI | 34 | 14 (41%) | 0 |
| Muse Code | 51 | 15 (29%) | 0 |
Which buyers it came up for
It surfaced most for requests written as senior engineer, in 36% of those sessions. Knowing which buyer already has the product in mind tells you which pages to fix first.
| Who is asking | Sessions | Raised it |
|---|---|---|
| Senior engineer | 464 | 167 (36%) |
| Enterprise team | 56 | 15 (27%) |
What Docker was up against
The full ranking in code sandboxes, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | E2B | 227 | 44% |
| 2 | Modal | 131 | 25% |
| 3 | Vercel Sandbox | 81 | 16% |
| 4 | Daytona | 73 | 14% |
| 5 | Anthropic Code Execution | 3 | 1% |
| 6 | Runloop Devboxes | 3 | 1% |
| 7 | Cloudflare Workers | 2 | 0% |
What this means
Read this row as context, not as a loss. On this board Docker is the thing underneath rather than one of the candidates: the database already in the repository, the protocol the alternatives implement, or the runtime they all run on. Our judge has an explicit rule for the clearest case: a vendor-neutral standard is never recorded as the winner, because it is the wiring and not the destination.
Where that reading does not apply, the causes below are the ones we see.
In our data the causes, in the order they occur:
- The quickstart does not run when pasted, so the agent abandoned it mid-integration.
- The documentation describes an interface that changed, so the generated code failed.
- The product name and the package name differ, so the install step went wrong.
- The fit was genuinely wrong for the repository, which is fine and worth knowing.
All but the last are fixable in days, and the reason is written down in the session transcript.
Where these numbers come from
The 520 sessions in code sandboxes 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 code sandboxes run can be replayed on the board.
If you work on Docker: 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 Docker?
They raise it but do not choose it. Across 182 sessions where Docker came up as a candidate, agents chose something else every time.
Does Claude Code recommend Docker?
In 0 of the 129 sessions in code sandboxes run with Claude Code, which is 0%.
Do different coding agents treat Docker differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 0% 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.
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.