seekdb
The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run, and more stable.
Could not verifysource: GitHubhomepageC++Apache-2.0commit ab26e64cfbb8
C++, Apache-2.0 licensed. The project labels itself: ai agents, copy on write, embedded database, full text search, hnsw, hybrid search, langchain and llamaindex.
Argusic could not get seekdb running. An Argusic agent installed it in 65 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
pyseekdb Python SDK 1.4.0.post1 installed and verified: embedded mode creates/upserts vector collections and returns semantically relevant query results. C++ source build blocked by missing system m4 (needed by bison 2.4.1 for SQL parser generation) and slow dependency mirror, though all 20 RPM dependency packages were successfully downloaded and extracted using libarchive wrappers.
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 20 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.
- OceanBase dependency mirror very slow (~40KB/s for large RPMs)30 minutes
- dep_create.sh requires rpm2cpio and cpio which are not installed15 minutes
- dep_create.sh requires wget which is not installed10 minutes
- C++ build blocked: bison requires m4 which is not installed in the container10 minutes
- Rust toolchain not active5 minutes
- Python pip install pyseekdb blocked by externally-managed-environment2 minutes
- Install time
- 65 minutes
- Cold machine to finish
- 65 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- pyseekdb embedded mode demonstrated end-to-end: created onnx embedding model (384-dim), upserted documents, refreshed index, queried with natural language, correctly retrieved semantically relevant results with distance scores
- Model tokens used
- 639,783
- Exact commit tested
- ab26e64cfbb8
- 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.
'test_depth': 'tier1_real',
'notes': 'pyseekdb Python SDK installed and verified end-to-end in embedded mode. C++ source bu…
'verified_how': 'pyseekdb embedded mode demonstrated end-to-end: created onnx embedding model (…
'final_state': 'pyseekdb Python SDK 1.4.0.post1 installed and verified: embedded mode creates/u…
}
print('ARGUSIC_RESULT: ' + json.dumps(result, ensure_ascii=False))
\" 2>&1" in /work/repo
succeeded in 0ms:
The final result has been printed. Let me verify the output is correct.
tokens used
639,783
The final result has been printed. Let me verify the output is correct.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
- Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- An agent with no time limit did not get it running.
- Took 65 minutes to install, slower than the median of the 11 comparable projects Argusic has measured.
Of the 12 ai-agents projects Argusic has installed and timed, seekdb was the 12th fastest to reach a running state, and 8 of 12 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 | 2/3 | Did not run | 20.00 | 0.40 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.24 |
Topics (from GitHub)
ai-agentscopy-on-writeembedded-databasefull-text-searchhnswhybrid-searchlangchainllamaindexmysqloceanbasepythonragsqlvector-databases
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/seekdb)Questions
- Does seekdb run?
- Argusic could not verify that seekdb runs. Argusic installed and launched it on a clean machine in 65 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test seekdb?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ab26e64cfbb8. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test seekdb?
- The run that produced this verdict cost $0.40: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does seekdb take to install?
- 65 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 seekdb need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing seekdb?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does seekdb compare with the alternatives?
- Of the 12 ai-agents projects Argusic has installed and timed, seekdb was the 12th fastest to reach a running state, and 8 of 12 reached one at all.
- Where is the evidence for seekdb?
- 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.