mnemon

LLM-supervised persistent memory for AI agents, graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

Runssource: GitHubhomepageGoApache-2.0commit e9ce9945b12f

Go, Apache-2.0 licensed. The project labels itself: agent framework, agent memory, ai agent, ai tools, claude, claude code, cli and context window.

mnemon runs. An Argusic agent installed it in 13 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

All 19 deterministic Go test packages pass, the mnemon binary builds and runs, and the installed binary at $GOBIN/mnemon successfully executes memory operations (remember, recall, status) on a real SQLite-backed store.

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
$0.01 (measured)
recorded runs
1
last tested
stars
732
forks
83
open issues
13
watchers
2
size
16 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.

Time lost to each failure while testing mnemon, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

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

  • Go compiler not found in container (no go binary)5 minutes
  • umask 0002 causes tests to fail — project root / tmp dirs are group/other-writable3 minutes
Install time
13 minutes
Cold machine to finish
5 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
make test exited 0 (19 packages, all tests passed); ./bin/mnemon remember/recall/status returned correct JSON; installed binary reports 'mnemon version dev'
Model tokens used
76,553
Exact commit tested
e9ce9945b12f
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.

/bin/sh -lc 'export PATH="/tmp/go/bin:$HOME/go/bin:$PATH" && export GOROOT=/tmp/go && export GOPATH…
 succeeded in 0ms:
mnemon version dev
Let me compute the times for the report.
exec
/bin/sh -lc 'echo "Build started at go build, completed at test pass. Errors: Go missing (installed…
 succeeded in 0ms:
Build started at go build, completed at test pass. Errors: Go missing (installed Go 1.27.2), umask …
All done. Let me compile the final report.
tokens used
76,553
All done. Let me compile the final report.

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.
  • Recovered from all 2 errors 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 Apache-2.0, as reported by its host.

What did not, or is not known

  • Took 13 minutes to install, slower than the median of the 63 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 64 agent-framework projects Argusic has installed and timed, mnemon was the 53rd fastest to reach a running state, and 51 of 64 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.

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 Runner1/3Runs100.000.01

Topics (from GitHub)

agent-frameworkagent-memoryai-agentai-toolsclaudeclaude-codeclicontext-windowdshdsh-pluginknowledge-graphllm-agentllm-memoryllm-supervisedmemoryopenclawpersistent-memory

Embed the badge

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

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

Questions

Does mnemon run?
Yes. mnemon runs. Argusic installed and launched it on a clean machine in 13 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test mnemon?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit e9ce9945b12f. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test mnemon?
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 mnemon take to install?
13 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 mnemon need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing mnemon?
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 mnemon compare with the alternatives?
Of the 64 agent-framework projects Argusic has installed and timed, mnemon was the 53rd fastest to reach a running state, and 51 of 64 reached one at all.
Where is the evidence for mnemon?
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