memlayer

Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.

Runs with mockssource: GitHubhomepagePythonMITcommit 5e95f44061a8

Python, MIT licensed. The project labels itself: agent, ai, ai infrastructure, context management, developer tools, embedded, graph database and knowledge graph.

memlayer runs, with stand-ins for the services it depends on. An Argusic agent installed it in 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.

memlayer 0.1.8 installs from source in a venv, all 58+ symbols import cleanly, core storage (ChromaDB + NetworkX) and search (SearchService) work end-to-end, entity deduplication merges 'Dr. Watson' into 'Dr. Emma Watson', SalienceGate correctly classifies salient vs. non-salient text in both LOCAL and LIGHTWEIGHT modes, and the Memory client initializes/shuts down gracefully.

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

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.16 (measured)
recorded runs
1
last tested
stars
309
forks
35
open issues
1
watchers
5
size
1 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 memlayer, 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.

  • pytest crashed on collection: test scripts with module-level `exit(0)` or side-effect code raised SystemExit3 minutes
  • ImportError: cannot import name 'OpenAIWrapper' from 'memlayer.wrappers.openai' — classes in wrapper files were named `OpenAI`, `Claude`, `Gemini`, `Ollama` but `client.py` and `wrappers/__init__.py` expected `OpenAIWrapper`, `ClaudeWrapper`, etc.2 minutes
Install time
5 minutes
Cold machine to finish
16 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
/home/runner/venv/bin/python ran a comprehensive 7-part integration test covering imports, NetworkX CRUD + entity dedup, ChromaDB read/write/search, SalienceGate in LOCAL + LIGHTWEIGHT modes, LocalEmbeddingModel inference, Memory client lifecycle, and SearchService hybrid vector+graph search. Pytest collected 4 test items (test_streaming.py), all skipped due to missing OPENAI_API_KEY.
Model tokens used
114,353
Exact commit tested
5e95f44061a8
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.

from memlayer.embedding_models import LocalEmbeddingModel, ArgusicEmbeddingModel, BaseEmbeddingModel
from memlayer.services import SearchService, ConsolidationService, CurationService, SchedulerService
from memlayer.config import set_debug_mode, is_debug_mode
from memlayer.observability import Trace
print('ALL 58+ symbols import cleanly')
\" 2>&1" in /work/repo
 succeeded in 11605ms:
ALL 58+ symbols import cleanly
Now I have all the evidence. Here is the final report:
tokens used
114,353
Now I have all the evidence. Here is 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

  • Installed in 5 minutes.
  • 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.

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

Of the 141 agent projects Argusic has installed and timed, memlayer was the 61st fastest to reach a running state, and 94 of 141 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 Runner1/3Runs with mocks92.000.16

Topics (from GitHub)

agentaiai-infrastructurecontext-managementdeveloper-toolsembeddedgraph-databaseknowledge-graphllmllm-memorymemoryopenaipersistent-memorypythonragretrievalretrieval-augmented-generationsemantic-searchtransformervector-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/memlayer.svg)](https://argusic.com/subject/memlayer)

Questions

Does memlayer run?
memlayer runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 5 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test memlayer?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5e95f44061a8. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test memlayer?
The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does memlayer take to install?
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 memlayer need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing memlayer?
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 memlayer compare with the alternatives?
Of the 141 agent projects Argusic has installed and timed, memlayer was the 61st fastest to reach a running state, and 94 of 141 reached one at all.
Where is the evidence for memlayer?
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