moai-adk
Agentic development harness for Claude Code, SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps.
Runssource: GitHubhomepageGoApache-2.0commit 7ad9f8534dc4
Go, Apache-2.0 licensed. The project labels itself: agentic ai, agentic coding, agentic workflow, ai agent, ai coding, anthropic, claude and claude code.
moai-adk runs. An Argusic agent installed it in 40 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
moai-adk v3.1.3 builds and runs. Binary at ./bin/moai responds to 'moai version' with v3.1.3. Test suite runs with 3 pre-existing failures (2 test-isolation, 1 codex-binary not available). templ code generation works. All ast-grep rule tests pass with version 0.40.5.
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.
- sg binary not in PATH (ast-grep sg CLI) — tests that exercise the real ast-grep scanner skipped5 minutes
- codex binary not in PATH — TestHandleCodexReviewGate_LiveCodexBlocksInjectionAndKey skipped (needs Claude Code CLI)
- TestCC_FactoryEntryThroughRunCC and TestGLM_FactoryWorkerEntry: test isolation bug — launchProjectRoot() uses resolveProjectDir() which ignores findProjectRootFn override, causing workers.json state pollution between subtests
- Install time
- 40 minutes
- Cold machine to finish
- 57 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- go test -race -count=1 ./... with MOAI_SKIP_LIVE_CODEX=1, all packages pass except 3 pre-existing failures (1 codex-binary skip, 2 test pollution bugs)
- Model tokens used
- 574,075
- Exact commit tested
- 7ad9f8534dc4
- 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.
Session started around 2026-09-10 01:23 UTC (go install) Let me get current time and calculate. exec /bin/sh -lc 'date -u +%s' in /work/repo succeeded in 0ms: 1789006718 The earliest download started around 01:23 UTC = epoch 1.789e9 + 4980 = ~1789006380 (approximately)… Given all the test runs (the full suite takes ~200+ seconds each and we ran it several times), plus… tokens used 574,075 The earliest download started around 01:23 UTC = epoch 1.789e9 + 4980 = ~1789006380 (approximately)… Given all the test runs (the full suite takes ~200+ seconds each and we ran it several times), plus…
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 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
- Took 40 minutes to install, slower than the median of the 7 comparable projects Argusic has measured.
Of the 8 agentic-ai projects Argusic has installed and timed, moai-adk was the 8th fastest to reach a running state, and 5 of 8 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.
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 | 100.00 | 0.33 | |
| Argusic Runner | 1/3 | Ran out of time | 0.00 | 0.30 |
Topics (from GitHub)
agentic-aiagentic-codingagentic-workflowai-agentai-codinganthropicclaudeclaude-codecli-toolcode-generationcode-qualityddddeveloper-toolsgogolangllmmulti-agentspec-driven-developmenttddvibe-coding
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/moai-adk)Questions
- Does moai-adk run?
- Yes. moai-adk runs. Argusic installed and launched it on a clean machine in 40 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test moai-adk?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7ad9f8534dc4. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test moai-adk?
- The run that produced this verdict cost $0.33: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does moai-adk take to install?
- 40 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 moai-adk need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing moai-adk?
- 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 moai-adk compare with the alternatives?
- Of the 8 agentic-ai projects Argusic has installed and timed, moai-adk was the 8th fastest to reach a running state, and 5 of 8 reached one at all.
- Where is the evidence for moai-adk?
- 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.