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 2.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

CodeGraphContext installed via venv/pip, imports cleanly, all 5 cgc doctor diagnostics pass, FalkorDB Lite backend connects and indexes real Python code into a queryable graph, all 1501 unit and 33 integration tests pass, and the MCP server initializes and responds to protocol handshake

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
$0.10 (measured)
recorded runs
2
last tested
stars
4,427
forks
851
open issues
191
watchers
23
size
42 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.

Time lost to each failure while testing CodeGraphContext, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Unit test failures: 2 Haskell parser tests failing due to tree-sitter-haskell grammar drift - the node name was misspelled `type_synomym` in an older grammar but is now `type_synonym` in the current grammar, causing the entire classes query to fail silently (the parse method catches the Exception and returns empty results)0.5 minutes
Install time
3 minutes
Cold machine to finish
29 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
`cgc doctor` exited 0 (all 5 checks passed, FalkorDB Lite connected); `cgc version` returned 'CodeGraphContext 0.6.13'; `cgc --database falkordb index sample_project` indexed 43 files, 138 functions, 36 classes, 112 CALLS edges; `cgc find name greet` returned 6 matches; `cgc analyze complexity` identified 1 over-threshold function; `cgc stats` reported 1 repo, 43 files, 181 functions, 36 classes; `cgc mcp start` responded with valid JSON-RPC initialization; unit tests: 1501 passed, 0 failed, 8 skipped; integration tests: 33 passed, 0 failed; MCP server initialization returned protocolVersion 2025-03-26, serverInfo name CodeGraphContext v0.6.13
Model tokens used
492,051
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.

┡━━━━━━━━━━━━━━╇━━━━━━━┩
│ Repositories │     1 │
│ Files        │    43 │
│ Functions    │   181 │
│ Classes      │    36 │
│ Modules      │    23 │
└──────────────┴───────┘
=== DONE ===
All systems verified. Here's the final report:
tokens used
492,051
All systems verified. Here's the final report:

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 2.5 minutes.
  • Recovered from all 1 error 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 2 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.
  • A quick evaluation: it was running 2.5 minutes after the clone.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.10
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 3 minutes, hitting 1 error 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. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test CodeGraphContext?
The run that produced this verdict cost $0.10: 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?
2.5 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 CodeGraphContext need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing CodeGraphContext?
1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for CodeGraphContext?
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