E2B
Open-source, secure environment with real-world tools for enterprise-grade agents.
Runs with mockssource: GitHubPythonApache-2.0commit ccaf9fc0ffe6
Python, Apache-2.0 licensed. The project labels itself: agent, ai, ai agent, ai agents, code interpreter, copilot, development and devtools.
E2B runs, with stand-ins for the services it depends on. An Argusic agent installed it in 33 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Dependencies installed, JS SDK builds (47 exports), Python SDK imports, CLI executable produces help and version output, and 323 JS tests plus ~450 Python tests pass using mocked HTTP endpoints.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- pnpm not on PATH (node v18.19.1 bundled)3 minutes
- uv not installed1 minute
- No E2B_API_KEY in environment
- Install time
- 33 minutes
- Cold machine to finish
- 33 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- pnpm install (exit 0); pnpm --dir packages/js-sdk build (exit 0); uv sync --dev (exit 0); CLI --version returns 2.20.0; npx vitest run --project unit with placeholder E2B_API_KEY prints 323 passed / 1 skipped / 0 failed; uv run pytest 30+ test files prints 294+122+83+15 passed; npx vitest run packages/cli prints 128 passed
- Model tokens used
- 777,081
- Exact commit tested
- ccaf9fc0ffe6
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- JS `sandboxTest`-based tests (create, network, snapshot, connect, fork, files, commands, etc.): 2…
- Python async/sync sandbox/API/template tests: same — need real creds
- CLI `template create` integration test: needs real creds
**Errors encountered during setup:**
1. `pnpm` not on PATH → installed node v22.18.0 via tarball, used corepack for pnpm
2. `uv` not installed → installed via `curl -LsSf https://astral.sh/uv/install.sh | sh`
3. No `E2B_API_KEY` in environment → placeholder `e2b_000...000` used for mock tests; real credenti…
exec
/bin/sh -lc "echo 'ARGUSIC_RESULT: {\"install_succeeded\": true, \"launch_succeeded\": true, \"inst…
succeeded in 0ms:
tokens used
777,081Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 33 minutes to install, slower than the median of the 41 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 42 agent projects Argusic has installed and timed, E2B was the 39th fastest to reach a running state, and 31 of 42 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.16 |
Topics (from GitHub)
agentaiai-agentai-agentscode-interpretercopilotdevelopmentdevtoolsgptgpt-4javascriptllmnextjsopenaipythonreactsoftwaretypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/e2b)Questions
- Does E2B run?
- E2B runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 33 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test E2B?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ccaf9fc0ffe6. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test E2B?
- The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does E2B take to install?
- 33 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does E2B need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing E2B?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does E2B compare with the alternatives?
- Of the 42 agent projects Argusic has installed and timed, E2B was the 39th fastest to reach a running state, and 31 of 42 reached one at all.
- Where is the evidence for E2B?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.