code-graph-rag
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Runssource: GitHubhomepagePythonMITcommit 511d6f6aecdc
Python, MIT licensed. The project labels itself: ai, ast, claude code, code analysis, code understanding, codebase search, developer tools and graph database.
code-graph-rag runs. An Argusic agent installed it in 52 minutes and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
code-graph-rag 0.0.985 installed and building from source; CLI responds with version 0.0.985; 185 non-integration tests pass, 45 skip due to missing optional grammars; Docker+Memgraph unavailable without Docker.
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 86.7 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.
- pytest-asyncio 1.3.0 incompatible with pytest 9.x (asyncio_mode config unknown)5 minutes
- python3-dev not installed; tree-sitter-c/C++ grammars fail to build from source (Python.h missing)
- Docker not available; Memgraph/Qdrant stack cannot start
- Install time
- 52 minutes
- Cold machine to finish
- 55 minutes
- Errors hit and fixed
- 3 hit, 1 fixed with no human help
- How the result was proved
- .venv/bin/pytest 17 test modules returned 185 passed, 45 skipped, zero failures; cgr --version returned code-graph-rag version 0.0.985
- Model tokens used
- 455,452
- Exact commit tested
- 511d6f6aecdc
- 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.
ENDJSON" in /work/repo
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 52, "errors": [{"msg": "py…
exec
/bin/sh -lc "ARGUSIC_RESULT: {\"install_succeeded\": true, \"launch_succeeded\": true, \"install_mi…
exited 127 in 0ms:
/bin/sh: 1: ARGUSIC_RESULT:: not found
exec
/bin/sh -lc "printf 'ARGUSIC_RESULT: {\"install_succeeded\": true, \"launch_succeeded\": true, \"in…
succeeded in 0ms:
tokens used
455,452Replay 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.
- 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
- Took 52 minutes to install, slower than the median of the 62 comparable projects Argusic has measured.
- Hit 3 errors during setup, 2 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 63 ai projects Argusic has installed and timed, code-graph-rag was the 62nd fastest to reach a running state, and 48 of 63 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.
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)
aiastclaude-codecode-analysiscode-understandingcodebase-searchdeveloper-toolsgraph-databaseknowledge-graphllmmcpmcp-servermemgraphmonorepomulti-languagepythonragretrieval-augmented-generationsemantic-searchtree-sitter
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/code-graph-rag)Questions
- Does code-graph-rag run?
- Yes. code-graph-rag runs. Argusic installed and launched it on a clean machine in 52 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test code-graph-rag?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 511d6f6aecdc. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test code-graph-rag?
- The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does code-graph-rag take to install?
- 52 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 code-graph-rag need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing code-graph-rag?
- 3 things broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does code-graph-rag compare with the alternatives?
- Of the 63 ai projects Argusic has installed and timed, code-graph-rag was the 62nd fastest to reach a running state, and 48 of 63 reached one at all.
- Where is the evidence for code-graph-rag?
- 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.