selfgraph
Build and query versioned knowledge graphs for AI agents, with any graph database.
Runssource: GitHubTypeScriptApache-2.0commit 97fb52be8e8e
TypeScript, Apache-2.0 licensed. The project labels itself: agent, graphs, knowledge graph, knowledge graphs, knowledge management and ontology.
selfgraph runs. An Argusic agent installed it in 0.4 minutes and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.
SelfGraph 0.2.2 installs cleanly on Python 3.12 via venv and runs its full test suite on embedded Kuzu with all deterministic tests passing. The CLI, SDK quickstart, and MCP server all function correctly. One test is OOM-bound in this container (test_kuzu_cancel_then_close).
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 90 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. 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.
- test_kuzu_cancel_then_close subprocess OOM-killed (SIGKILL -9) on container with ~1GB RAM: spawns 50 Kuzu databases at 128MB each2 minutes
- kuzu 0.11.3 needs a larger buffer pool than 64MB for 513 relation versions1 minute
- Install time
- under a minute
- Cold machine to finish
- 48 minutes
- Errors hit and fixed
- 2 hit, 1 fixed with no human help
- How the result was proved
- pytest with SELFGRAPH_TEST_STORE=kuzu: 789 collected, ~766 passed, ~22 skipped, 1 OOM failure unrelated to code. Quickstart asyncio.run() returned correct context. CLI insert+retrieve round-trip worked.
- Model tokens used
- 120,033
- Exact commit tested
- 97fb52be8e8e
- 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.
3. **Inter-test Kuzu lock contention**: When test suites ran in sequence, stale `.kuzu` files from …
**Test results (SELFGRAPH_TEST_STORE=kuzu, 789 collected, 10 deselected)**:
- All deterministic tests pass with Kuzu backend
- ~22 skipped (cypher dialect, HydraDB-specific, FalkorDB-specific, concurrent — all unrelated to K…
- 1 failure: OOM on `test_kuzu_cancel_then_close` (container memory limit)
- The buffer pool test and all conformance-critical tests pass
**End-to-end verification**: The README quickstart ran and returned `GRAPH | Jane Doe -[WORKS_AT]->…
exec
/bin/sh -lc "echo \"ARGUSIC_RESULT: {\\\"install_succeeded\\\": true, \\\"launch_succeeded\\\": tru…
succeeded in 0ms:
tokens used
120,033Replay 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 0.4 minutes, faster than the median of the 140 comparable projects Argusic has measured.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Hit 2 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 141 agent projects Argusic has installed and timed, selfgraph was the 10th fastest to reach a running state, and 94 of 141 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 0.4 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)
agentgraphsknowledge-graphknowledge-graphsknowledge-managementontology
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/selfgraph)Questions
- Does selfgraph run?
- Yes. selfgraph runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test selfgraph?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 97fb52be8e8e. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test selfgraph?
- The run that produced this verdict cost $0.18: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does selfgraph take to install?
- 0.4 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 selfgraph need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing selfgraph?
- 2 things 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 selfgraph compare with the alternatives?
- Of the 141 agent projects Argusic has installed and timed, selfgraph was the 10th fastest to reach a running state, and 94 of 141 reached one at all.
- Where is the evidence for selfgraph?
- 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.