solomd
A markdown editor, and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.
Runssource: GitHubhomepageTypeScriptMITcommit 47d5f2e263cd
TypeScript, MIT licensed. The project labels itself: ai, android, autogit, byok, cross platform, ios, knowledge base and local first.
solomd runs. An Argusic agent installed it in 8 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.
MCP server compiles, passes all 36 tests, and serves notes over stdio JSON-RPC with all 13 tools verified end-to-end including write_note and append_to_note creating files on disk; JS library tests pass 76/76; vite frontend build produces dist/; Tauri desktop app cannot compile without system -dev packages that require root access.
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 92 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.
- Tauri desktop app cannot build (no system .deb -dev packages)25 minutes
- pnpm npm global install failed (EACCES)1 minute
- pnpm ignored build scripts (core-js, esbuild)
- test-self.mjs imports pinyin/simplifiedToTraditional/traditionalToSimplified from wrong module (chinese.ts instead of chinese-convert.ts)
- Astro web build fails (Node.js 18.19.1 < 18.20.8 required)
- Install time
- 8 minutes
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 5 hit, 4 fixed with no human help
- How the result was proved
- MCP server: solomd-mcp --version printed 'solomd-mcp 0.4.1'; cargo test --release ran 36 tests (28+3+5) all passed; end-to-end stdio test: initialize, tools/list (13 tools), list_notes, read_note, search, write_note (confirmed file on disk), append_to_note (confirmed appended content) all returned correct JSON-RPC responses. JS tests: npx tsx test-self.mjs returned '55 passed / 0 failed'; npx tsx test-slash-blocks.mjs returned 'OK · slash-blocks · 21 entries · all assertions passed'. Frontend: pnpm build (vue-tsc + vite) exited 0, 3382 modules transformed.
- Model tokens used
- 120,035
- Exact commit tested
- 47d5f2e263cd
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Install succeeded**: Rust (1.100.0) via rustup, pnpm (12.18.0) via npm, pnpm dependencies for `ap… **What works:** - **MCP server** (`mcp-server/`) - built, all 36 tests passed in debug and release, binary responds… - **Frontend build** (`app/`) - `pnpm build` (vue-tsc + vite) succeeded, 3382 modules transformed. - **JS library tests** - `test-self.mjs` (55 passed) and `test-slash-blocks.mjs` (21 passed) via ts… **What failed and why:** - **Tauri desktop app** (`app/src-tauri/`) requires `libwebkit2gtk-4.1-dev`, `libglib2.0-dev`, `lib… - **Web/website** (`web/`) - Astro 5.x requires Node.js >= 18.20.8, container has 18.19.1. **Errors encountered and fixed:** - **pnpm install EACCES** - npm global install failed; worked around by setting `npm config set pre… - **pnpm "Ignored build scripts"** - fixed with `pnpm approve-builds --all` for both `app/` and `we… - **test-self.mjs import bug** - imported `simplifiedToTraditional`, `traditionalToSimplified`, `pi…
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.
- 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 8 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.
- Hit 5 errors during setup, 1 of which were not solved.
Of the 237 ai projects Argusic has installed and timed, solomd was the 156th fastest to reach a running state, and 168 of 237 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 8 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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 96.00 | 0.10 | |
| Argusic Runner | 1/3 | Runs with mocks | 88.00 | 0.24 |
Topics (from GitHub)
aiandroidautogitbyokcross-platformiosknowledge-baselocal-firstmarkdownmarkdown-editormcpmcp-servernote-takingobsidian-alternativetauritldrawtypora-alternativevuewhiteboardwikilinks
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/solomd)Questions
- Does solomd run?
- Yes. solomd runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test solomd?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 47d5f2e263cd. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test solomd?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does solomd take to install?
- 8 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 solomd need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing solomd?
- 5 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 solomd compare with the alternatives?
- Of the 237 ai projects Argusic has installed and timed, solomd was the 156th fastest to reach a running state, and 168 of 237 reached one at all.
- Where is the evidence for solomd?
- 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.