mcp-memory-service
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
Runssource: GitHubPythonApache-2.0commit 4a2253459760
Python, Apache-2.0 licensed. The project labels itself: agent memory, agentic ai, ai agents, autogen, claude, crewai, knowledge graph and langgraph.
mcp-memory-service 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.
mcp-memory-service 11.13.0 installed from source via pip install -e '.[dev]', the uvicorn server starts on 127.0.0.1:9791 (HTTP) with sqlite_vec backend, health endpoint returns 200, memory CRUD operations work end to end, and the full test suite passes except for one benchmark test that fails due to hash-embedding fallback (no ML dependencies).
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_stop_refuses_to_kill_foreign_listener_without_force failed: `_find_process_on_port` uses `lsof` which is not installed in this container, so it returns None and the foreign listener is never detected5 minutes
- test_retrieve_exact_query_finds_something (benchmark) fails: hash-embedding fallback mode cannot perform accurate semantic search without ONNX/transformers dependencies
- Install time
- under a minute
- Cold machine to finish
- 20 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- curl -s http://127.0.0.1:9791/api/health returned 200 with {'status':'healthy'}; POST /api/memories stored memory and returned success; GET /api/memories listed stored memories; POST /api/search returned search results; pytest tests/unit/ ran 599 passed, 6 skipped, 1 xfailed; pytest tests/services/ tests/server/ tests/api/ tests/web/ ran 283 passed, 4 skipped, 1 xpassed; pytest tests/storage/ ran 271 passed, 14 skipped, 4 xfailed, 1 xpassed; pytest remaining ran 696 passed, 3 skipped, 7 xfailed; total ~1600+ tests passed
- Model tokens used
- 139,032
- Exact commit tested
- 4a2253459760
- 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.
All observations are recorded. Let me now produce the final report.
exec
/bin/sh -lc 'kill 5433 2>/dev/null; kill 5457 2>/dev/null; pkill -f "uvicorn" 2>/dev/null; pkill -f…
exited 143 in 0ms:
Here is the final report:
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 0.5, "…
All ~1600+ tests pass (pre-existing benchmark failure excluded), the server launches and responds t…
tokens used
139,032
Here is the final report:
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 0.5, "…
All ~1600+ tests pass (pre-existing benchmark failure excluded), the server launches and responds t…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 5 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 Apache-2.0, 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 6 agent-memory projects Argusic has installed and timed, mcp-memory-service was the 1st 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.
- 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-memoryagentic-aiai-agentsautogenclaudecrewaiknowledge-graphlanggraphlong-term-memorymcpmcp-servermemorymodel-context-protocolmulti-agentopen-sourceragsemantic-searchsqlite-vecvector-databasevector-storage
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/mcp-memory-service)Questions
- Does mcp-memory-service run?
- Yes. mcp-memory-service 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 mcp-memory-service?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4a2253459760. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test mcp-memory-service?
- The run that produced this verdict cost $0.24: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does mcp-memory-service 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 mcp-memory-service need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing mcp-memory-service?
- 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 mcp-memory-service compare with the alternatives?
- Of the 6 agent-memory projects Argusic has installed and timed, mcp-memory-service was the 1st fastest to reach a running state, and 6 of 6 reached one at all.
- Where is the evidence for mcp-memory-service?
- 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.