codebase-memory-mcp
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph, average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Runssource: GitHubhomepageCMITcommit c38aa35c2773
C, MIT licensed. The project labels itself: aider, ast, claude code, code analysis, code intelligence, codex, cursor and cypher.
codebase-memory-mcp runs. An Argusic agent installed it in 11.7 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
codebase-memory-mcp v0.10.8 is installed, the MCP server is configured in Codex CLI config.toml with hooks, and the repository is indexed with a knowledge graph of 21,005 nodes and 119,361 edges, all 15 MCP tools verified working.
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.
- Full index mode (index_repository without --mode flag) killed by OOM (signal 9, peak 1689 MB RSS against 491 MB budget)2 minutes
- npm install via npx failed: activation_transaction I/O failed due to group-writable npm cache directory permissions (mode 0775)1.5 minutes
- Install time
- 12 minutes
- Cold machine to finish
- 15 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- Model tokens used
- 121,038
- Exact commit tested
- c38aa35c2773
- Container image
- sha256:4c3d41857be3
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.
- How the result was proved
- runs before 2026-09-07 did not record the command used to check the result
- 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.
Start: 1788455700 Now: 1788456400 Total time: about 11 minutes (660 seconds). Let me finalize the report. All errors encountered: 1. First attempt at `install -y` via npx failed due to npm directory permissions being group-writab… 2. First index attempt (`index_repository` without `--mode`) was killed by OOM (signal 9, peak ~168… tokens used 121,038 Total time: about 11 minutes (660 seconds). Let me finalize the report. All errors encountered: 1. First attempt at `install -y` via npx failed due to npm directory permissions being group-writab… 2. First index attempt (`index_repository` without `--mode`) was killed by OOM (signal 9, peak ~168…
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 11.7 minutes.
- 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 MIT, as reported by its host.
- Measured 3 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 3/3 | Ran out of time | 0.00 | 0.16 | |
| Argusic Runner | 2/3 | Runs | 100.00 | 0.04 | |
| Argusic Runner | 1/3 | Ran out of time | 0.00 | 0.24 |
Topics (from GitHub)
aiderastclaude-codecode-analysiscode-intelligencecodexcursorcypherdeveloper-toolsgemini-cligraph-visualizationkilocodeknowledge-graphmcpmcp-servermodel-context-protocolopencodesqlitetree-sitterwindsurf
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/codebase-memory-mcp)Questions
- Does codebase-memory-mcp run?
- Yes. codebase-memory-mcp runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test codebase-memory-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c38aa35c2773. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test codebase-memory-mcp?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does codebase-memory-mcp take to install?
- 11.7 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 codebase-memory-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing codebase-memory-mcp?
- 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.
- Where is the evidence for codebase-memory-mcp?
- 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.