claude-obsidian
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.
Runssource: GitHubPythonMITcommit ad67087cad22
Python, MIT licensed. The project labels itself: agent skills, ai note taking, ai second brain, claude code, claude code skill, claude memory, claude plugin and karpathy llm wiki.
claude-obsidian runs. An Argusic agent installed it in 5 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The 15 Codex skills installed successfully, and the full test suite, vault lifecycle, local BM25 retrieval, strict lint, and a reproducible 199-file release build all passed using only local resources.
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.
- First test fixture used [[Cobalt Lantern]] while the file was Cobalt-Lantern.md, so strict lint reported 3 dead links and 1 orphan (5 issues).1 minute
- A fresh-vault setup command was rejected by the command guard because it began with rm -rf.
- capture adapters --vault PATH exited with argparse error: unrecognized arguments.
- Assumed setup-retrieve.sh preview output was JSON, causing JSONDecodeError.
- Install time
- 5 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- make test exited 0 and printed 'All hermetic tests and executable contracts passed'; contracts --verify returned ok=true, valid=true, errors=[]; release build produced 199 files with ok=true and two builds had identical SHA-256 817813fecb3086c76dc2126cba6a28ad9e988e4371610b9073fb1513b9955723; capture apply created a raw file matching its source SHA-256; strict lint exited 0 with issues=0 over 5 pages; retrieve.py --vault VAULT 'cobalt lantern' --top 1 --no-rerank exited 0 with strategy=bm25-only and top_path=wiki/concepts/Cobalt-Lantern.md.
- Model tokens used
- 118,925
- Exact commit tested
- ad67087cad22
- 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.
"ok": true, "schema": "claude-obsidian.package-validation.v1", "skills": 15 } exec /bin/sh -c 'date -u +%Y-%m-%dT%H:%M:%SZ; vault="$(cat /tmp/argusic-vault-path)"; python3 scripts/cl… succeeded in 31ms: 2026-11-03T05:13:06Z lint_rc=0 issues=0 pages=5 tokens used 118,925
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.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 5 minutes to install, slower than the median of the 113 comparable projects Argusic has measured.
Of the 114 agent-skills projects Argusic has installed and timed, claude-obsidian was the 73rd fastest to reach a running state, and 84 of 114 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 5 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)
agent-skillsai-note-takingai-second-brainclaude-codeclaude-code-skillclaude-memoryclaude-pluginkarpathy-llm-wikiknowledge-graphknowledge-managementnote-takingnotion-alternativeobsidianobsidian-aiobsidian-pluginobsidian-second-brainopen-sourcepersonal-knowledge-managementpkmsecond-brain
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/claude-obsidian)Questions
- Does claude-obsidian run?
- Yes. claude-obsidian runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test claude-obsidian?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ad67087cad22. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test claude-obsidian?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does claude-obsidian take to install?
- 5 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 claude-obsidian need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing claude-obsidian?
- 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 claude-obsidian compare with the alternatives?
- Of the 114 agent-skills projects Argusic has installed and timed, claude-obsidian was the 73rd fastest to reach a running state, and 84 of 114 reached one at all.
- Where is the evidence for claude-obsidian?
- 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.