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 2.1 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

MCP Memory Service v11.13.0 installed in a venv at /work/repo/.venv; 3196 of 3199 tests pass; the HTTP REST API server starts, serves /api/health (200), /api/memories (stores and lists memories), /api/search (semantic search with hash embeddings), and the dashboard at / (200)

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
$0.08 (measured)
recorded runs
2
last tested
stars
2,137
forks
433
open issues
32
watchers
14
size
82 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 mcp-memory-service, 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.

  • uv command not found on PATH for CLI integration tests1 minute
  • REST API returned 401 Unauthorized (authorization_required) on first launch1 minute
  • 3 pre-existing flaky test failures in tests/unit/test_cli_lifecycle.py (test_stop_refuses_to_kill_foreign_listener_without_force, test_stop_kills_untracked_memory_server_listener, test_stop_force_kills_foreign_listener) — subprocess socket listener timeout race in constrained env
Install time
2 minutes
Cold machine to finish
13 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
pip install -e .[dev] succeeded; pytest ran 3196 passed, 126 skipped, 13 xfailed, 4 xpassed, 3 failed (pre-existing flaky); server launched on port 19393, curl /api/health returned 200 {"status":"healthy"}, POST /api/memories stored a memory successfully, POST /api/search returned results with similarity scores, GET /api/memories returned total:2, GET / returned 200
Model tokens used
160,871
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 2, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

--- GET /api/memories ---
Total memories: 2
--- Dashboard ---
Dashboard HTTP: 200
Everything works end-to-end. Let me kill any remaining servers and compile the final result.
exec
/bin/sh -lc "pkill -f \"mcp_memory_service.cli.main\" 2>/dev/null; pkill -f \"uvicorn.*18989\\|uvic…
 exited 143 in 0ms:
Here's my complete findings report:
tokens used
160,871
Here's my complete findings 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.
  • Installed in 2.1 minutes, faster than the median of the 27 comparable projects Argusic has measured.
  • Recovered from all 3 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.
  • Measured 2 times, so the result is not a one-off.

Of the 28 agent-memory projects Argusic has installed and timed, mcp-memory-service was the 9th fastest to reach a running state, and 24 of 28 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 2.1 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.08
Argusic Runner1/3Runs100.000.24

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.

[![Tested by Argusic](https://argusic.com/badge/mcp-memory-service.svg)](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 2 minutes, hitting 3 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. 2 attempts are 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 $0.08: 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?
2.1 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?
3 things broke in the recorded run, and 3 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 28 agent-memory projects Argusic has installed and timed, mcp-memory-service was the 9th fastest to reach a running state, and 24 of 28 reached one at all.
Where is the evidence for mcp-memory-service?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion