projectmem

Open-source coding agents memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.

Runssource: GitHubhomepagePythonMITcommit e8d73137acde

Python, MIT licensed. The project labels itself: agent memory, agentic ai, ai agents, ai memory, ai tools, antigravity, claude and claude code.

projectmem runs. An Argusic agent installed it in 16 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

projectmem 0.3.3 is installed in a venv at /work/repo/.venv, all 279 tests pass, the pjm CLI works end-to-end (init, doctor, help), and the MCP server module loads without error.

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
$0.01 (measured)
recorded runs
2
last tested
stars
878
forks
54
open issues
1
watchers
8
size
3 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.

Install time
16 minutes
Cold machine to finish
1 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
pytest ran 279 passed in 9.6s; pjm --help printed 23 commands; pjm doctor reported all-clear; pjm init created full projectmem skeleton in a test repo
Model tokens used
21,335
Exact commit tested
e8d73137acde
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.

**Tests**: `pytest` ran 279 tests and all **279 passed** in 9.6s — no failures, no errors, no skips.
**CLI verification**: `pjm --help` prints all 23 commands. `pjm doctor` reports everything checks o…
**MCP server**: `pjm-mcp --help` exits silently (expected for a stdio-based MCP server — it waits f…
No third-party keys needed, no mocks required, no errors to fix.
tokens used
21,335
Everything works beautifully with zero errors. Let me compile the final report.
**Install**: Created a venv and ran `pip install -e ".[dev]"` — all dependencies installed cleanly …
**Tests**: `pytest` ran 279 tests and all **279 passed** in 9.6s — no failures, no errors, no skips.
**CLI verification**: `pjm --help` prints all 23 commands. `pjm doctor` reports everything checks o…
**MCP server**: `pjm-mcp --help` exits silently (expected for a stdio-based MCP server — it waits f…
No third-party keys needed, no mocks required, no errors to fix.

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.
  • 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.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Took 16 minutes to install, slower than the median of the 27 comparable projects Argusic has measured.

Of the 28 agent-memory projects Argusic has installed and timed, projectmem was the 23rd 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.
  • 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.01
Argusic Runner1/3Runs100.000.02

Topics (from GitHub)

agent-memoryagentic-aiai-agentsai-memoryai-toolsantigravityclaudeclaude-codecoding-agents-memorycoding-assistantcoding-memorycursordeveloper-toolsknowledge-managementlocal-firstmcp-servermem0-alternativememorymodel-context-protocolpython

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/projectmem.svg)](https://argusic.com/subject/projectmem)

Questions

Does projectmem run?
Yes. projectmem runs. Argusic installed and launched it on a clean machine in 16 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test projectmem?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit e8d73137acde. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test projectmem?
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 projectmem take to install?
16 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 projectmem need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing projectmem?
Nothing did, in the recorded run: zero errors between clone and running.
How does projectmem compare with the alternatives?
Of the 28 agent-memory projects Argusic has installed and timed, projectmem was the 23rd fastest to reach a running state, and 24 of 28 reached one at all.
Where is the evidence for projectmem?
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