CodeGraphContext

An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.

Runssource: GitHubhomepagePythonMITcommit 8e08dcc9a0e8

Python, MIT licensed. The project labels itself: codegraph, codegraphcontext, hacktoberfest2025 and social winter of code.

CodeGraphContext runs. An Argusic agent installed it in 12 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

CodeGraphContext 0.6.13 installed and working: CLI, FalkorDB/KuzuDB/LadybugDB backends, indexing, MCP server, and 1615 of 1627 tests pass.

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
$0.13 (measured)
recorded runs
1
last tested
stars
4,233
forks
833
open issues
116
watchers
24
size
41 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
12 minutes
Cold machine to finish
36 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
pytest tests/unit/ (1501 passed), tests/integration/ (107 passed), tests/e2e/test_user_journeys.py (2 passed), tests/test_mcp_sse.py (2 passed). CLI --version returns 0.6.13. cgc doctor all green. Indexed 43 files against FalkorDB Lite. MCP server responded to tools/list.
Model tokens used
122,674
Exact commit tested
8e08dcc9a0e8
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.

- `python -m codegraphcontext --help` — all commands listed
- `python -m codegraphcontext --version` → `CodeGraphContext 0.6.13`
- `cgc doctor` — all checks passed (FalkorDB Lite, tree-sitter, permissions)
- `cgc index` on sample project — indexed 43 files, 138 functions, 36 classes, 112 CALLS edges
- `cgc stats` — confirmed 1 repo, 43 files, 181 functions, 36 classes
**Backend verification** (all three embedded backends):
- FalkorDB Lite ✅
- KuzuDB ✅
- LadybugDB ✅ (via CGC's `LadybugDBManager`)
**MCP server**: started via stdio, responded to `tools/list` with 20+ tools
**Parity test**: skipped (requires Neo4j server at localhost:7687, not available in container — but…
The only issue was LadybugDB's C API library (`get_capi_module()`) not being present — but CGC's ac…

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 12 minutes.
  • 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.

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.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.13

Topics (from GitHub)

codegraphcodegraphcontexthacktoberfest2025social-winter-of-code

Embed the badge

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

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

Questions

Does CodeGraphContext run?
Yes. CodeGraphContext runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test CodeGraphContext?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8e08dcc9a0e8. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test CodeGraphContext?
The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does CodeGraphContext take to install?
12 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 CodeGraphContext need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing CodeGraphContext?
Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for CodeGraphContext?
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.

Discussion