mempalace
The best-benchmarked open-source AI memory system. And it's free.
Runssource: GitHubhomepagePythonMITcommit a9f345cc6325
Python, MIT licensed. The project labels itself: ai, chromadb, llm, mcp, memory and python.
mempalace runs. An Argusic agent installed it in 5 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
MemPalace 3.8.0 installs, builds, passes all 4587 core tests, and runs a full init-mine-search pipeline end-to-end using local ChromaDB and ONNX embeddings with no external API calls.
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
- 5 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- pytest tests/ --ignore=tests/benchmarks -v exited 0 with 4587 passed; mempalace init --yes --no-llm created config; mempalace mine filed 1 drawer; mempalace search returned the verbatim content with cosine_sim=0.74 bm25=0.863
- Model tokens used
- 46,704
- Exact commit tested
- a9f345cc6325
- 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.
**Install** — `pip install -e ".[dev]"` in a Python 3.12 venv completed without errors. All depende… **Test suite** — `pytest tests/ --ignore=tests/benchmarks -v` ran **4587 passed, 31 skipped** in ~2… **CLI verification** — `mempalace --version` printed `MemPalace 3.8.0`. **End-to-end real behavior** — I stood up a fresh palace from scratch: 1. `mempalace init /tmp/test_palace --yes --no-llm` → created `mempalace.yaml` with wing `test_pala… 2. Wrote a note `"My name is Alice. I work on the GraphQL API migration project."` into `notes.txt` 3. `mempalace --palace /tmp/test_palace mine /tmp/test_palace --wing test_palace` → downloaded the … 4. `mempalace --palace /tmp/test_palace search "GraphQL API migration"` → returned the verbatim tex… 5. `mempalace --palace /tmp/test_palace status` → reported 1 drawer in `test_palace / general` No external APIs were contacted (local ChromaDB + local ONNX embedding only). No mocks needed. ``` ```
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 3 times, so the result is not a one-off.
What did not, or is not known
- Took 5 minutes to install, slower than the median of the 36 comparable projects Argusic has measured.
Of the 37 ai projects Argusic has installed and timed, mempalace was the 20th fastest to reach a running state, and 30 of 37 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 5 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)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/mempalace)Questions
- Does mempalace run?
- Yes. mempalace runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test mempalace?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a9f345cc6325. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test mempalace?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does mempalace 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 mempalace need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing mempalace?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does mempalace compare with the alternatives?
- Of the 37 ai projects Argusic has installed and timed, mempalace was the 20th fastest to reach a running state, and 30 of 37 reached one at all.
- Where is the evidence for mempalace?
- All 3 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.