From the experiment

Do coding agents recommend E2B?

E2B is the most chosen code sandbox, taking 42% of 299 judged code sandboxes sessions. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

E2B is the most chosen code sandbox, taking 42% of 299 judged code sandboxes sessions. It was also raised as a candidate in 157 further sessions without being chosen.

This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in code sandboxes inside a realistic codebase. Not what a chat assistant says about E2B. What an agent actually installed.

The numbers

CategoryCode sandboxes
Sessions in the category299
Sessions where E2B was chosen127
Install share42%
Rank in category1 of 7
Codebases it won in5
Raised as a candidate, not chosen157
Chosen when considered45%
Sitee2b.dev

By agent

The three agents treat E2B very differently. Cursor chose it in 85% of its sessions in this category and Codex in 4%, a spread of 81 points.

AgentSessionsChose E2BShare
Claude Code953638%
Codex10244%
Cursor1028785%

A single blended install share would report the midpoint and hide both ends. If most of your users run Codex, your real position here is 4%, not 42%.

By who was asking

E2B does much better with one kind of buyer than another. It won 46% of sessions asked as senior engineer and 10% of those asked as enterprise team.

Who is askingSessionsChose E2BShare
Senior engineer26912446%
Enterprise team30310%

What E2B was up against

The full ranking in code sandboxes, from the same sessions:

#ProductRuns wonShare
1E2B (this page)12742%
2Modal7425%
3Daytona4716%
4Vercel Sandbox4314%
5Anthropic Code Execution31%
6Runloop Devboxes31%
7Cloudflare Workers21%

What this means

Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.

The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.

Where these numbers come from

The 299 sessions in code sandboxes 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 code sandboxes run can be replayed on the board.

If you work on E2B: 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 E2B?

Yes. E2B was chosen in 127 of the 299 judged sessions in code sandboxes, a 42% install share, ranking first in its category.

Does Claude Code recommend E2B?

In 36 of the 95 sessions in code sandboxes run with Claude Code, which is 38%.

Do different coding agents treat E2B differently?

Yes, and by a wide margin. Cursor chose it in 85% of its runs and Codex in 4%.

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 E2B considered but not chosen?

It was raised as a candidate in 157 sessions without being chosen, and chosen in 127. That is a 45% 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.

Read next

All library pages