kensaku
Search inside documents, code, and even screenshots - instantly and locally. A free, open-source file launcher with OCR, semantic search, and MCP agent access.
Runssource: GitHubRustMITcommit c2da457a5320
Rust, MIT licensed. The project labels itself: ai agents, desktop, desktop search, file search, full text search, launcher, local first and mcp.
kensaku runs. An Argusic agent installed it in 68 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Rust test suite passes with 291 tests, CLI binary builds and responds to --help, TypeScript type-check passes; the Tauri desktop app cannot be launched without a full WebKitGTK runtime environment
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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Missing system dev libraries: libwebkit2gtk-4.1-dev, libgtk-3-dev, librsvg2-dev, libayatana-appindicator3-dev, patchelf, and ~30 transitive dev packages (no root, can't apt install)50 minutes
- No Rust toolchain installed in container2 minutes
- Bun not available to run make install1 minute
- kensaku-daemon binary does not respond to --help (hangs waiting for socket connection)
- Install time
- 68 minutes
- Cold machine to finish
- 40 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- cargo test --manifest-path src-tauri/Cargo.toml exited 0, 291 passed, 0 failed, 1 golden_set test passed; kensaku-cli --help printed usage; npx tsc --noEmit exited 0
- Model tokens used
- 525,044
- Exact commit tested
- c2da457a5320
- 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 525,044 Now I have all the data I need. Let me compile the final result. **Summary of what was done:** 1. **System dependencies**: No root access, so I downloaded ~630 `.deb` packages and extracted them… 2. **Rust toolchain**: Installed via rustup (rustc 1.99.1, cargo 1.99.1). 3. **JS dependencies**: `npm install` succeeded (Node 18, though some packages wanted >=20 — warnin… 4. **cargo check** on `src-tauri` passed (0 errors). 5. **291 Rust tests passed**, 0 failed, 14 ignored (benches/manual tests). 6. **CLI binary** `kensaku-cli` built and ran `--help` successfully. 7. **TypeScript type-check** (`npx tsc --noEmit`) passed cleanly. The Tauri desktop app itself could not be launched because `libwebkit2gtk-4.1.so.0` and WebKit help…
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 4 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.
What did not, or is not known
- Took 68 minutes to install, slower than the median of the 106 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 107 ai-agents projects Argusic has installed and timed, kensaku was the 105th fastest to reach a running state, and 79 of 107 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
Topics (from GitHub)
ai-agentsdesktopdesktop-searchfile-searchfull-text-searchlauncherlocal-firstmcpocropen-sourceprivacyrustsearchsemantic-searchtauriwindows
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/kensaku)Questions
- Does kensaku run?
- Yes. kensaku runs. Argusic installed and launched it on a clean machine in 68 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test kensaku?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c2da457a5320. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test kensaku?
- The run that produced this verdict cost $0.20: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does kensaku take to install?
- 68 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 kensaku need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing kensaku?
- 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 kensaku compare with the alternatives?
- Of the 107 ai-agents projects Argusic has installed and timed, kensaku was the 105th fastest to reach a running state, and 79 of 107 reached one at all.
- Where is the evidence for kensaku?
- 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.