agent-memory
Long-term memory runtime for AI agents, plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.
Runssource: GitHubPythonMITcommit 7c4a00da1270
Python, MIT licensed. The project labels itself: agent memory, ai agents, claude code, codex, llm, local first, long term memory and markdown.
agent-memory runs. An Argusic agent installed it in 2 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
All 6 packages installed and passing 788 tests with ruff and mypy clean; store initialized and CLI end-to-end verified: wrote a fact with mem record, retrieved it with mem recall (BM25 score returned), and read full body with mem read --level full.
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.
- Install time
- 2 minutes
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- pytest tests/ returned 788 passed, 1 skipped; ruff check returned all checks passed; mypy returned no issues in 77 source files; mem init + mem record + mem recall + mem read --level full all returned valid output
- Model tokens used
- 30,208
- Exact commit tested
- 7c4a00da1270
- 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.
outline: [] text: The sky is blue on a clear day Everything works end-to-end with zero errors and zero API keys needed. Here's the summary: **Install**: `uv sync --all-extras` installed all 6 packages (`agent-memory-core`, `agent-memory-cl… **Tests**: `pytest tests/` — **788 passed, 1 skipped** in 34.75s. `ruff check .` — all checks passe… **E2E verification**: Initialized a store (`mem init`), wrote a memory (`mem record`), retrieved it… tokens used 30,208 Everything works end-to-end with zero errors and zero API keys needed. Here's the summary: **Install**: `uv sync --all-extras` installed all 6 packages (`agent-memory-core`, `agent-memory-cl… **Tests**: `pytest tests/` — **788 passed, 1 skipped** in 34.75s. `ruff check .` — all checks passe… **E2E verification**: Initialized a store (`mem init`), wrote a memory (`mem record`), retrieved it…
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 minutes, faster than the median of the 13 comparable projects Argusic has measured.
- Nothing broke on the way: zero errors between clone and running.
- 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 14 agent-memory projects Argusic has installed and timed, agent-memory was the 4th fastest to reach a running state, and 14 of 14 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 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
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-memoryai-agentsclaude-codecodexllmlocal-firstlong-term-memorymarkdownmcppythonretrievalsqlite
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agent-memory)Questions
- Does agent-memory run?
- Yes. agent-memory runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test agent-memory?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7c4a00da1270. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test agent-memory?
- The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agent-memory take to install?
- 2 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 agent-memory need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agent-memory?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does agent-memory compare with the alternatives?
- Of the 14 agent-memory projects Argusic has installed and timed, agent-memory was the 4th fastest to reach a running state, and 14 of 14 reached one at all.
- Where is the evidence for agent-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.