cortexdb

Local-first AI agent memory with a knowledge graph, ontology constraints, and traceable reasoning, all in one SQLite file.

Runssource: GitHubhomepageGoMITcommit 42e70daa12d8

Go, MIT licensed. The project labels itself: agent memory, ai memory, claude code, codex, embeddings, full text search, go and golang.

cortexdb runs. An Argusic agent installed it in 4 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

CortexDB v2.113.0 builds from source, all 25 test packages pass, and the gRPC+REST server starts on lexical mode (no API keys) serving health, info, knowledge, memory, graph, and query endpoints with no errors.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.13 (measured)
recorded runs
1
last tested
stars
530
forks
36
open issues
2
watchers
3
size
30 MB
created
last push

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.

Install time
4 minutes
Cold machine to finish
15 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
go test ./... -count=1 -timeout 180s: all 25 packages passed. curl -sf http://127.0.0.1:47840/v1/health returned {"ok":true}. ./cortexdb-grpc -addr 127.0.0.1:47841 -health returned 'ok 127.0.0.1:47841 v2.113.0 db=... embedder=none'. curl -sfX POST http://127.0.0.1:47840/v1/recall -H 'Content-Type: application/json' -d '{"query":"Alice tabs","scope":"user","user_id":"testuser"}' returned context_pack with memories.
Model tokens used
252,394
Exact commit tested
42e70daa12d8
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.

 succeeded in 11778ms:
ok    github.com/liliang-cn/cortexdb/v2/pkg/rpcserver  0.595s
ok    github.com/liliang-cn/cortexdb/v2/pkg/semantic-router  0.007s
ok    github.com/liliang-cn/cortexdb/v2/pkg/sqldialect  0.003s
===
{"ok":true}===
2026/10/20 13:32:20 ok 127.0.0.1:47841 v2.113.0 db=/tmp/ctest/e2e2.db embedder=none
All 25 packages pass on a clean single run (the `-count=2` flake is a known expvar re-registration …
2026-10-20T13:32:29.424353Z ERROR codex_core::session: failed to record rollout items: thread 01a15…
tokens used
252,394
All 25 packages pass on a clean single run (the `-count=2` flake is a known expvar re-registration …

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 4 minutes.
  • Nothing broke on the way: zero errors between clone and running.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

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 4 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.13

Topics (from GitHub)

agent-memoryai-memoryclaude-codecodexembeddingsfull-text-searchgogolanggraphraghindsightknowledge-graphllmmcpragrdfsparqlsqlitevector-databasevector-search

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/cortexdb.svg)](https://argusic.com/subject/cortexdb)

Questions

Does cortexdb run?
Yes. cortexdb runs. Argusic installed and launched it on a clean machine in 4 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test cortexdb?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 42e70daa12d8. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test cortexdb?
The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does cortexdb take to install?
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 cortexdb need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing cortexdb?
Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for cortexdb?
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.

Discussion