eve
The Open Framework for Building Agents
Runssource: GitHubTypeScriptApache-2.0commit a7b0fb2bf24d
TypeScript, Apache-2.0 licensed. The project labels itself: agent, framework, harness, javascript, markdown, sandbox, typescript and vercel.
eve runs. An Argusic agent installed it in 13 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
pnpm install, pnpm build, all 938 unit/integration test files (9758 tests), linting, guard invariants, typecheck on the main eve package, and the eve CLI binary all pass without errors on Node 24.21.0 with pnpm 12.7.0.
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 100 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.
- Install time
- 13 minutes
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- pnpm test:unit exited 0 (807 files, 8726 passed); pnpm test:integration exited 0 (131 files, 1032 passed); node packages/eve/bin/eve.js --version returned 0.68.0; pnpm dev started weather-agent fixture, curl returned 200 on /
- Model tokens used
- 168,948
- Exact commit tested
- a7b0fb2bf24d
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
tokens used 168,948 All tasks completed with zero failures. Here's the full report: **Install & build**: `pnpm install` succeeded (2383 packages, 53s). `pnpm build` succeeded (6 packa… **Test results**: - **Unit**: 807 test files, 8726 passed, 1 skipped — all green - **Integration**: 131 test files, 1032 passed — all green - **Typecheck** (main `eve` package): passed (0 errors) - Typecheck across the full workspace hit OOM (on a 51-package parallel turbo run in a memory-const… **CLI verification**: `node packages/eve/bin/eve.js --version` returned `0.68.0`. `--help` listed a… **Dev server verification**: `pnpm dev` started the weather-agent fixture, reporting `server listen… No errors were hit during install, build, or test execution. No fixes were needed.
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
- Reached a running state on a clean machine, with the session recorded.
- Nothing broke on the way: zero errors between clone and running.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Took 13 minutes to install, slower than the median of the 59 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 60 agent projects Argusic has installed and timed, eve was the 39th fastest to reach a running state, and 41 of 60 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- Following its own README: the documented path worked with nothing to fix.
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
Topics (from GitHub)
agentframeworkharnessjavascriptmarkdownsandboxtypescriptvercelworkflows
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/eve)Questions
- Does eve run?
- Yes. eve runs. Argusic installed and launched it on a clean machine in 13 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test eve?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a7b0fb2bf24d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test eve?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does eve take to install?
- 13 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 eve need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing eve?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does eve compare with the alternatives?
- Of the 60 agent projects Argusic has installed and timed, eve was the 39th fastest to reach a running state, and 41 of 60 reached one at all.
- Where is the evidence for eve?
- 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.