Yes. ai-memory runs. Argusic installed and launched it on a clean machine in 60 minutes, hitting 4 errors on the way, and recorded the session.

How did Argusic test ai-memory?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 49147a5d1736. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test ai-memory?

The run that produced this verdict cost $0.53: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does ai-memory take to install?

60 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 ai-memory need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing ai-memory?

4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.

Where is the evidence for ai-memory?

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.

ai-memory

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Runssource: GitHubRustMITcommit 49147a5d1736

Rust, MIT licensed.

ai-memory runs. An Argusic agent installed it in 60 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

ai-memory 2.4.1 builds from source as a single 38 MB binary, passes all 3457 crate tests (0 failures), starts an MCP+HTTP server on port 49374 that applies all DB migrations, serves the wiki web UI at /web with HTTP 200, and downloads a local embedding model automatically.
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: $0.53 (measured)
recorded runs: 1
last tested: 2026-09-28
stars: 8,512
forks: 579
open issues: 29
watchers: 50
size: 19 MB
created: 2026-05-21
last push: 2026-09-28

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-28. 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 ai-memory, 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.

Lock contention from concurrent cargo build processes (LTO/test builds)5 minutes
MCP test binary (101 MB LTO build) required >120s, got killed by timeout2 minutes
Rust 1.95 toolchain not pre-installed in container1 minute
cargo t alias requires cargo-nextest but cargo-nextest was not installed1 minute

Install time: 60 minutes
Cold machine to finish: 85 minutes
Errors hit and fixed: 4 hit, 4 fixed with no human help
How the result was proved: cargo test -p <each-crate> and target/debug/deps/<test-binary> for all 10 crate test suites: 3457 passed, 0 failed; curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:49374/web/ returned 200; curl -X POST http://127.0.0.1:49374/mcp returned 405; binary --version returned 'ai-memory 2.4.1'
Model tokens used: 321,371
Exact commit tested: 49147a5d1736
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.

| ai-memory-consolidate | 319 | 315 passed, 4 ignored |
| ai-memory-web | 114 | 114 passed |
| ai-memory-mcp | 469 | 468 passed, 1 ignored |
| ai-memory-workstream | 96 | 96 passed |
| ai-memory-cli | 972 | 971 passed, 1 ignored |
**Total: 3457 tests, 0 failures, 10 ignored**
**Server launch:** `ai-memory serve --transport http --enable-web` started successfully, applied al…
**Obstacles:**
- Rust 1.95 toolchain not pre-installed; rustup fixed it (~1 min)
- Background build processes caused cargo lock contention; fixed by killing orphans and running seq…
- `cargo t` alias needs `cargo-nextest` but the project works fine with `cargo test`; used test bin…
- MCP test binary (101M, LTO) took ~65s and timed out at 120s initially

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 4 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 MIT, as reported by its host.

What did not, or is not known

Took 60 minutes to install, slower than the median of the 5 comparable projects Argusic has measured.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 6 Rust projects Argusic has installed and timed, ai-memory was the 6th fastest to reach a running state, and 6 of 6 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.

Run history

tested by	attempt	outcome	score	cost USD	when
Argusic Runner	1/3	Runs	100.00	0.53	2026-09-28 11:41 UTC

Embed the badge

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

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

Questions

Does ai-memory run?: Yes. ai-memory runs. Argusic installed and launched it on a clean machine in 60 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test ai-memory?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 49147a5d1736. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test ai-memory?: The run that produced this verdict cost $0.53: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does ai-memory take to install?: 60 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 ai-memory need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing ai-memory?: 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does ai-memory compare with the alternatives?: Of the 6 Rust projects Argusic has installed and timed, ai-memory was the 6th fastest to reach a running state, and 6 of 6 reached one at all.
Where is the evidence for ai-memory?: 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.