kuku

Open-source local-first Markdown workspace with wiki, AI editing, and encrypted sync.

Runs with mockssource: GitHubhomepageTypeScriptMITcommit ea07b629ead9

TypeScript, MIT licensed. The project labels itself: ai, ai notes, editor, encrypted sync, knowledge management, local first, macos and markdown.

kuku runs, with stand-ins for the services it depends on. An Argusic agent installed it in 23 minutes and hit 7 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

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

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.49 (measured)
recorded runs
1
last tested
stars
234
forks
38
open issues
3
watchers
3
size
77 MB
created
last push

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.

Time lost to each failure while testing kuku, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Rust not pre-installed2 minutes
  • Go not pre-installed2 minutes
  • Node v18 too old for vitest 4.x (needs node:util.styleText)2 minutes
  • pnpm not pre-installed (needed node v18)1 minute
  • kuku-ai linking fails on Linux: no WebKit/GTK2/JavaScriptCore system libraries
  • Go server tests need PostgreSQL
Install time
23 minutes
Cold machine to finish
24 minutes
Errors hit and fixed
7 hit, 7 fixed with no human help
How the result was proved
kuku-indexer: cargo test -> 22 passed, 0 failed; web app: pnpm test -> 2 test files, 8 passed; web app build: astro build -> 16 pages; Go server build: go build ./... -> exit 0; Go binary: go build -o bin/server ./cmd/server -> 51MB binary
Model tokens used
228,691
Exact commit tested
ea07b629ead9
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.

- Go v1.27.3 (`go.dev/dl/` uses dots, not dashes in the URL)
- Node v22.13.0 (vitest 4.x needs `node:util.styleText` which v18 doesn't have)
**Build & Test results:**
- **kuku-indexer** — `cargo test`: 22 passed, 0 failed
- **kuku-contract** — `cargo test`: 24 ignored (generated code doc-tests), 0 failed
- **kuku-ai** — compiles with mocked `.pc` files; linking fails at test time (needs `libwebkit2gtk-…
- **Web app** — `pnpm test`: 2 test files, 8 passed; `pnpm build`: Astro built 16 pages ✓
- **Go server** — `go build ./...`: exit 0; 51MB `bin/server` binary produced
**What didn't work (both unfixable without system packages):**
1. `kuku-ai` crate tests can't link on Linux — requires WebKit2GTK/JavaScriptCore system libraries …
2. Go server tests need PostgreSQL — no DB available in the container
The project requires no real third-party API credentials for the work that can be verified here.

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 7 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, 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 23 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 237 ai projects Argusic has installed and timed, kuku was the 212th fastest to reach a running state, and 168 of 237 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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks92.000.49

Topics (from GitHub)

aiai-noteseditorencrypted-syncknowledge-managementlocal-firstmacosmarkdownnote-takingnotesobsidian-alternativepersonal-knowledge-managementsecond-braintauriwiki

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/kuku.svg)](https://argusic.com/subject/kuku)

Questions

Does kuku run?
kuku runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 23 minutes, hitting 7 errors on the way, and recorded the session.
How did Argusic test kuku?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit ea07b629ead9. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test kuku?
The run that produced this verdict cost $0.49: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does kuku take to install?
23 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 kuku need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing kuku?
7 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does kuku compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, kuku was the 212th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for kuku?
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.

Discussion