E2B
Open-source, secure environment with real-world tools for enterprise-grade agents.
Runs with mockssource: GitHubhomepagePythonApache-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 9 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The repository installs and builds with the pinned toolchain, the CLI launches at version 2.20.0, the no-credential CLI and Python offline suites pass, and an isolated installed CLI completed a mocked template build including a COPY upload.
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, refreshed . 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.
- CLI template create with COPY failed: Cannot find package 'glob' imported from packages/cli/dist/index.js3 minutes
- pnpm and uv were not installed; container Node 18.19.1 did not meet repository Node >=22 requirement2 minutes
- CLI template create with COPY then failed: Cannot find package 'tar' imported from packages/cli/dist/index.js2 minutes
- Credential-dependent template-create test failed before test execution when E2B_API_KEY was absent2 minutes
- Install time
- 9 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pnpm --dir packages/cli test exited 0 with 129 passed and 8 skipped; uv run pytest tests/test_*.py exited 0 with 342 passed; isolated installed CLI completed template create against a local schema-shaped mock with exit 0 and recorded 1 upload, 1 trigger, and 1 status poll; e2b --version printed 2.20.0
- Model tokens used
- 533,776
- 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.
**Verification** - `pnpm install --frozen-lockfile`: exit 0, 625 packages. - `pnpm run format`, `pnpm run lint`, `pnpm run typecheck`: all exit 0. - Full workspace build: exit 0. - CLI suite: `129 passed | 8 skipped`, 18 files passed, 2 skipped. - Python SDK offline tests: `342 passed`. - JS connection-config tests: `43 passed`. - Installed packed CLI in an isolated prefix: `e2b --version` printed `2.20.0`. - Installed CLI `template create` against a local mock: exit 0, one COPY upload, one build trigger,… - All three Python distributions built successfully via `uv build`. **Limits** The live sandbox/integration suites still require a real `E2B_API_KEY` and E2B backend; attempting …
Replay 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 4 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.
- Measured 2 times, so the result is not a one-off.
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 9 minutes to install, slower than the median of the 137 comparable projects Argusic has measured.
Of the 138 agent projects Argusic has installed and timed, E2B was the 84th fastest to reach a running state, and 92 of 138 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 | 2/3 | Runs with mocks | 92.00 | 0.29 | |
| 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 9 minutes, hitting 4 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. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test E2B?
- The run that produced this verdict cost $0.29: 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?
- 9 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?
- 4 things broke in the recorded run, and 4 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 138 agent projects Argusic has installed and timed, E2B was the 84th fastest to reach a running state, and 92 of 138 reached one at all.
- Where is the evidence for E2B?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.