obsidian-mind
A self-organizing Obsidian vault that gives AI coding agents persistent memory. Claude Code, Codex CLI, Gemini CLI.
Runssource: GitHubTypeScriptMITcommit af615d100a1d
TypeScript, MIT licensed. The project labels itself: ai agents, claude code, codex cli, gemini cli, knowledge management, obsidian, obsidian vault and persistent memory.
obsidian-mind runs. An Argusic agent installed it in 4 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Obsidian Mind v8.4.0 vault ready with all 5 lifecycle hooks functional, MCP launchers working, 1533/1533 tests passing, and TypeScript typecheck clean
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.
- Node v18.19.1 lacks --experimental-strip-types required by TypeScript hook scripts2 minutes
- Install time
- 4 minutes
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm test exited 0, 1533 passed, 0 failed; tsc --noEmit passed clean; all 5 hook scripts execute without error
- Model tokens used
- 50,653
- Exact commit tested
- af615d100a1d
- 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.
2. **Ran the full test suite** — 1533 tests passed, 0 failures across 268 suites. 3. **Ran TypeScript typecheck** — `tsc --noEmit` passed with 0 errors. 4. **Verified all hook scripts** run without errors: `session-start.ts`, `classify-message.ts`, `va… 5. **Verified MCP server launcher** (`om-mcp.mjs`, `qmd-mcp.mjs`) — they launch correctly; QMD serv… ### What was missing / fixed: | Issue | Fix | |-------|-----| | Node v18 lacks `--experimental-strip-types` | Installed Node 22.23.3 via nvm | ### What's optional (not required for vault operation): - QMD (`@tobilu/qmd`) for semantic search — the vault works without it, falling back to grep - Obsidian desktop app (unavailable in this container, not needed for hook scripts) - The `om` MCP server worked as a transparent shim
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.
- Installed in 4 minutes, faster than the median of the 29 comparable projects Argusic has measured.
- Recovered from all 1 error 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 30 ai-agents projects Argusic has installed and timed, obsidian-mind was the 11th fastest to reach a running state, and 20 of 30 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 4 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
Topics (from GitHub)
ai-agentsclaude-codecodex-cligemini-cliknowledge-managementobsidianobsidian-vaultpersistent-memorysecond-braintemplate
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/obsidian-mind)Questions
- Does obsidian-mind run?
- Yes. obsidian-mind runs. Argusic installed and launched it on a clean machine in 4 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test obsidian-mind?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit af615d100a1d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test obsidian-mind?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does obsidian-mind take to install?
- 4 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 obsidian-mind need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing obsidian-mind?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does obsidian-mind compare with the alternatives?
- Of the 30 ai-agents projects Argusic has installed and timed, obsidian-mind was the 11th fastest to reach a running state, and 20 of 30 reached one at all.
- Where is the evidence for obsidian-mind?
- 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.