myPKA
AI-powered Personal Knowledge Assistance in a folder. Built on the ICOR methodology. Plain markdown. Any LLM. Yours forever.
Runs with mockssource: GitHubhomepagePythonMITcommit 9b31da920c2a
Python, MIT licensed. The project labels itself: agentic, ai agents, ai team, claude code, claude cowork, cursor, gemini cli and icor.
myPKA runs, with stand-ins for the services it depends on. An Argusic agent installed it in 5 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 29 Python scripts compile and pass syntax validation. The harness generator (scaffold-init.py) checks and applies successfully, validating 56 generated files against their source hashes. Team validation confirms a compliant structure. All 9 skills pass 146 checks. The expansion-pack test suite passes 21/21 cases. The 4 shell scripts have valid shebangs.
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.
- The full red-test suite (run-red-tests.py) cannot run from a standalone myPKA checkout — it requires a combined ICOR for Life + myPKA deployment (mode A or B). This is by design and documented in the code at line 117-130. Exit 2, no FAIL lines.15 minutes
- check-icor-concepts.py requires source root at /work/icor-for-life (sibling directory) which does not exist in this checkout. Exit 2.
- check-version-bump.py requires --base to be a git ref/commit reachable in the repository. No tags exist in this checkout (shallow/fresh clone). Exit 2.
- Install time
- 5 minutes
- Cold machine to finish
- 7 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- All 29 Python scripts pass syntax check (py_compile). scaffold-init.py check/apply: 56 generated files match hashes, 65 files current, 9 host links in place. validate-team.py: OK compliant. check-release-blockers.py: OK no blockers (255 files read). check-room-literals.py: T2 GREEN. check-agent-shim-mcp.py: OK. skill-doctor.py --all: 18 skills, 146 checks, all OK. test-expansion-pack: 21 test cases, Ran OK. resolve.py: team root discovered correctly at /work/repo. session-start.py: ritual runs, identifies missing content source binding as expected.
- Model tokens used
- 120,251
- Exact commit tested
- 9b31da920c2a
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
succeeded in 0ms:
Updater-POC tests: Traceback (most recent call last):
File "<frozen runpy>", line 198, in _run_module_as_main
File "<frozen runpy>", line 88, in _run_code
File "/usr/lib/python3.12/unittest/__main__.py", line 18,
t7b-legacy-upgrade syntax: OK
Now I have a clear picture. Let me give the comprehensive final assessment.
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 5.0, "…
tokens used
120,251
Now I have a clear picture. Let me give the comprehensive final assessment.
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 5.0, "…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
- Installed in 5 minutes, faster than the median of the 5 comparable projects Argusic has measured.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 6 agentic projects Argusic has installed and timed, myPKA was the 2nd fastest to reach a running state, and 3 of 6 reached one at all.
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 | 1/3 | Runs with mocks | 92.00 | 0.10 |
Topics (from GitHub)
agenticai-agentsai-teamclaude-codeclaude-coworkcursorgemini-cliicorknowledge-managementlocal-firstlogseq-alternativemarkdownmem-alternativemulti-agentnotion-alternativeobsidianpersonal-knowledge-architecturepersonal-knowledge-managementpkmproductivity
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/mypka)Questions
- Does myPKA run?
- myPKA runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 5 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test myPKA?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 9b31da920c2a. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test myPKA?
- 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 myPKA 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 myPKA need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing myPKA?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does myPKA compare with the alternatives?
- Of the 6 agentic projects Argusic has installed and timed, myPKA was the 2nd fastest to reach a running state, and 3 of 6 reached one at all.
- Where is the evidence for myPKA?
- 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.