mneme
🧠The memory that dreams, cross-session memory for DeepSeek Harness. Local SQLite + Markdown mirrors, autoDream consolidation, 4-way recall (keyword/vector/BM25/entity), and a memory panel. 10 model tools, MCP server, CLI.
Runssource: GitHubhomepageJavaScriptMITcommit 1e9ac51a83ff
JavaScript, MIT licensed. The project labels itself: agent memory, agent memory system, agentic ai, autodream, claude, codex, deepseek harness and dsh plugin.
mneme runs. An Argusic agent installed it in 0.5 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 2587 tests pass on node 22.23.4 with the libc inference fix in build-runtime-manifest.mjs and runtime-manifest.json regenerated; src/ and lib/ synced; both prior failing tests (try 1777 libc filtering and 1778 manifest drift) now pass.
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
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.
- test 1777: libc filter could not find musl variants because npm lockfile v3 has no explicit libc field on linuxmusl packages30 minutes
- test 1778: committed runtime-manifest.json out of sync with package-lock.json after node version upgrade2 minutes
- Install time
- under a minute
- Cold machine to finish
- 31 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- npm test exited 0, 2587 passed, 0 failed
- Model tokens used
- 101,218
- Exact commit tested
- 1e9ac51a83ff
- 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.
=== sync check === ✓ src/ 与 lib/ 一致（82 个文件） All three verification gates pass. Here's the summary: - **npm test**: 2587 passed, 0 failed - **runtime-manifest --check**: consistent with lockfile, glibc filtering now correctly drops 2 mus… - **check-sync**: 82 files consistent between src/ and lib/ tokens used 101,218 All three verification gates pass. Here's the summary: - **npm test**: 2587 passed, 0 failed - **runtime-manifest --check**: consistent with lockfile, glibc filtering now correctly drops 2 mus… - **check-sync**: 82 files consistent between src/ and lib/
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 0.5 minutes, faster than the median of the 24 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.
- 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.
Of the 25 agent-memory projects Argusic has installed and timed, mneme was the 3rd fastest to reach a running state, and 22 of 25 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.
- A quick evaluation: it was running 0.5 minutes after the clone.
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
Topics (from GitHub)
agent-memoryagent-memory-systemagentic-aiautodreamclaudecodexdeepseek-harnessdsh-pluginknowledge-managementllmlong-term-memorymcpmcp-servermemory-consolidationmodel-context-protocolpersistent-memoryragsemantic-searchvector-search
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/mneme)Questions
- Does mneme run?
- Yes. mneme runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test mneme?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1e9ac51a83ff. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test mneme?
- The run that produced this verdict cost $0.20: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does mneme take to install?
- 0.5 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 mneme need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing mneme?
- 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 mneme compare with the alternatives?
- Of the 25 agent-memory projects Argusic has installed and timed, mneme was the 3rd fastest to reach a running state, and 22 of 25 reached one at all.
- Where is the evidence for mneme?
- 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.