automem

Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.

Runs with mockssource: GitHubhomepagePythonMITcommit 0e8c4174b799

Python, MIT licensed. The project labels itself: ai, ai memory, anthropic, automem, falkordb, graph database, llm and memory.

automem runs, with stand-ins for the services it depends on. An Argusic agent installed it in 3 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

In this container: make install succeeds, python app.py boots and serves /health, the unit suite passes 664 tests, and authenticated store/recall/query/delete flows work over HTTP against the schema-compatible in-memory mock.

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 56 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
56 / 100
cost of the verifying run
$0.30 (measured)
recorded runs
2
last tested
stars
832
forks
115
open issues
28
watchers
10
size
4 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.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • docker compose/services unavailable in container (no docker binary)
  • model download for embeddings missing (no network during app init); onnx runtime OK via cached model
Install time
3 minutes
Cold machine to finish
15 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
make test (pytest -m unit) => 664 passed, 1 skipped; HTTP checks: POST /memory 201, GET /recall 200 with matching memory, DELETE /memory/by-tag 200, GET /health 200; mock-backed run: 7/7 harness tests passed
Model tokens used
1,496,996
Exact commit tested
0e8c4174b799
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.

exec
/bin/sh -lc 'cd /work/repo && git status --short; echo "---"; ls -d tests/endtoend 2>&1; echo "---"…
 succeeded in 0ms:
ls: cannot access 'tests/endtoend': No such file or directory
218
__pycache__
conftest.py
test_standup_e2e.py
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 3, "er…
tokens used
1,496,996
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 3, "er…

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 3 minutes, faster than the median of the 236 comparable projects Argusic has measured.
  • Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

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.

Of the 237 ai projects Argusic has installed and timed, automem was the 86th fastest to reach a running state, and 168 of 237 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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Did not run20.000.08
Argusic Runner1/3Runs with mocks92.000.30

Topics (from GitHub)

aiai-memoryanthropicautomemfalkordbgraph-databasellmmemoryqdrantragvector-database

Embed the badge

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

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

Questions

Does automem run?
automem runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 3 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test automem?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0e8c4174b799. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test automem?
The run that produced this verdict cost $0.30: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does automem take to install?
3 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 automem need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing automem?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does automem compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, automem was the 86th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for automem?
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.

Discussion