cog
Embedded Graph Database for Python. Lives inside your Python process. Quick setup. No server. Runs in notebooks, apps, even your browser.
Runssource: GitHubhomepagePythonMITcommit 5be9863fce7e
Python, MIT licensed. The project labels itself: database, embedded database, embedded graph database, embedding, graph, graph database, knowledge graph and linkeddata.
cog runs. An Argusic agent installed it in 0.2 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
CogDB 4.0.2 installed in a Python venv; all 573 non-cloud tests pass; graph traversal, embeddings (k_nearest, sim, embedding_stats), and benchmark all execute correctly.
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.
- externally-managed-environment blocked system pip install1 minute
- Install time
- under a minute
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pytest -m 'not cloud' returned 573 passed, 0 failed; README quick-start and embedding examples verified with assertions
- Model tokens used
- 23,732
- Exact commit tested
- 5be9863fce7e
- 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.
- System `pip install` failed with `externally-managed-environment` → fixed by using `python3 -m ve… - `test/bench.py` requires matplotlib (optional visualization script) — not a project dependency er… No real credentials were needed; all testing was done locally with the embedded store. tokens used 23,732 All tasks are complete. Here is my final report: **Install**: Created a virtual environment (system Python 3.12 was externally managed), pip-install… **Tests**: Ran `pytest -m "not cloud"` — 573 passed, 47 deselected, 0 failed. Also manually verifie… **Errors**: Two minor issues encountered and both either fixed or not applicable: - System `pip install` failed with `externally-managed-environment` → fixed by using `python3 -m ve… - `test/bench.py` requires matplotlib (optional visualization script) — not a project dependency er… No real credentials were needed; all testing was done locally with the embedded store.
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 0.2 minutes, faster than the median of the 13 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.
- Measured 2 times, so the result is not a one-off.
Of the 14 database projects Argusic has installed and timed, cog was the 2nd fastest to reach a running state, and 13 of 14 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 0.2 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)
databaseembedded-databaseembedded-graph-databaseembeddinggraphgraph-databaseknowledge-graphlinkeddatanetwork-graphnosqlpythonpython-databasepython-graph-databaserdftriple-storetriplesvectors
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/cog)Questions
- Does cog run?
- Yes. cog runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test cog?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5be9863fce7e. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test cog?
- The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does cog take to install?
- 0.2 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 cog need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing cog?
- 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 cog compare with the alternatives?
- Of the 14 database projects Argusic has installed and timed, cog was the 2nd fastest to reach a running state, and 13 of 14 reached one at all.
- Where is the evidence for cog?
- 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.