amical
🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open source models, works offline, fast and accurate.
Runssource: GitHubhomepageTypeScriptMITcommit 19d414a91e0a
TypeScript, MIT licensed. The project labels itself: ai, ai note taking app, asr, dictate, dictation, dictation tool, electron and local ai.
amical runs. An Argusic agent installed it in 24 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Installation completed: Node 24.10.0, pnpm 10.34.5, all 1566 packages installed, whisper native addon compiled (.node binary at packages/whisper-wrapper/native/linux-x64/whisper.node), electron 44.3.0 available, workspace builds pass, and the test suite runs (149/150 test files pass, 1505/1508 tests pass, 3 pre-existing failures in shortcut-manager-unassign.test.ts).
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.
- libgomp.a static linking failed: not compiled with -fPIC, cannot link into shared .node extension5 minutes
- System Node.js v18.19.1 too old, project requires >=242 minutes
- onnxruntime-node postinstall failed trying to download Windows CUDA binaries from NuGet on Linux1 minute
- pnpm not available on system PATH1 minute
- Install time
- 24 minutes
- Cold machine to finish
- 23 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pnpm test exited with 149 passed / 1 failed (1505 tests passed, 3 failed); electron --version returned v44.3.0
- Model tokens used
- 79,641
- Exact commit tested
- 19d414a91e0a
- 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.
- Initialized the `whisper.cpp` git submodule - Ran `pnpm install --frozen-lockfile` ## Errors Encountered 1. **onnxruntime-node postinstall** — tried to download a CUDA 12 NuGet package (Windows paths on L… 2. **whisper-wrapper native addon linking** — `libgomp.a` static library wasn't compiled with `-fPI… 3. **Node.js version too old** — system had v18.19.1, project requires ≥24. Fixed by downloading an… 4. **pnpm not installed** — not on system PATH. Fixed by installing via npm to user prefix. ## Launch / Verification - **Electron binary** responds: `v44.3.0` confirmed via `electron --version --no-sandbox` - **Test suite**: `pnpm test` → **149 passed, 1 failed** (150 test files), **1505 tests passed, 3 f… - The 3 failures are pre-existing (in `shortcut-manager-unassign.test.ts`, related to expected mock… - The whisper native addon `whisper.node` (2.9 MB) was successfully compiled and installed
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 24 minutes to install, slower than the median of the 101 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 102 ai projects Argusic has installed and timed, amical was the 90th fastest to reach a running state, and 71 of 102 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)
aiai-note-taking-appasrdictatedictationdictation-toolelectronlocal-aimacosmcpmeeting-notesnextjsollamaproductivityself-hostedspeech-to-texttranscriptionwhisperwindows
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/amical)Questions
- Does amical run?
- Yes. amical runs. Argusic installed and launched it on a clean machine in 24 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test amical?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 19d414a91e0a. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test amical?
- The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does amical take to install?
- 24 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 amical need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing amical?
- 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 amical compare with the alternatives?
- Of the 102 ai projects Argusic has installed and timed, amical was the 90th fastest to reach a running state, and 71 of 102 reached one at all.
- Where is the evidence for amical?
- 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.