zero
The coding agent that answers to you, your model, your machine, your rules.
Runssource: GitHubhomepageGoMITcommit 99721c762f37
Go, MIT licensed. The project labels itself: ai, ai agent, anthropic, cli, code assistant, coding agent, developer tools and gemini.
zero runs. An Argusic agent installed it in 7 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Zero 0.9.0 builds from source, all 77 test packages pass (including race-enabled run), the release build tooling works, and the binary responds to --help and version commands. Execution requires a provider API key (zero exec / TUI).
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, 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.
- Go 1.26.6+ not found in PATH; required to build from source1 minute
- npm global install (npm install -g @gitlawb/zero) failed with EACCES on /usr/local/lib/node_modules1 minute
- GOPATH and GOROOT were the same directory after extraction, causing Go warning
- Install time
- 7 minutes
- Cold machine to finish
- 9 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- go build -o zero ./cmd/zero succeeded producing 40MB binary; go test ./... -count=1 passed all 77 packages; go run ./cmd/zero-release smoke printed 'zero smoke check passed (0.9.0)'; ./zero version printed 'zero 0.9.0'
- Model tokens used
- 42,947
- Exact commit tested
- 99721c762f37
- 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.
ok github.com/Gitlawb/zero/internal/workspaceseed 0.015s ok github.com/Gitlawb/zero/internal/workspacetrust 0.043s ok github.com/Gitlawb/zero/internal/worktrees 0.767s ok github.com/Gitlawb/zero/internal/zerocommands 0.016s ok github.com/Gitlawb/zero/internal/zerogit 1.064s ok github.com/Gitlawb/zero/internal/zeroruntime 0.008s Everything passed. Let me compile the results. 2026-11-13T16:25:40.266681Z ERROR codex_core::session: failed to record rollout items: thread 01a1d… 2026-11-13T16:25:40.266724Z ERROR codex_core::session: failed to record rollout items: thread 01a1d… tokens used 42,947 Everything passed. Let me compile the results.
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.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 7 minutes to install, slower than the median of the 234 comparable projects Argusic has measured.
Of the 235 ai projects Argusic has installed and timed, zero was the 142nd fastest to reach a running state, and 167 of 235 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.
- A quick evaluation: it was running 7 minutes after the clone.
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)
aiai-agentanthropicclicode-assistantcoding-agentdeveloper-toolsgeminillmmcpollamaopenaiterminal
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/zero)Questions
- Does zero run?
- Yes. zero runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test zero?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 99721c762f37. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test zero?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does zero take to install?
- 7 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 zero need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing zero?
- 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 zero compare with the alternatives?
- Of the 235 ai projects Argusic has installed and timed, zero was the 142nd fastest to reach a running state, and 167 of 235 reached one at all.
- Where is the evidence for zero?
- 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.