codex-with-chatgpt

ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.

Runssource: GitHubTypeScriptMITcommit a9f91cd98df1

TypeScript, MIT licensed. The project labels itself: ai agents, chatgpt, codex, mcp, model context protocol and oauth.

codex-with-chatgpt runs. An Argusic agent installed it in 3.2 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

pnpm install and pnpm build succeed, all 164/164 tests pass, the c2c CLI starts the bridge (observed on port 48765), reports status, and stops cleanly, and its help/version commands respond correctly

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 60 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
60 / 100
cost of the verifying run
$0.01 (measured)
recorded runs
2
last tested
stars
6,371
forks
577
open issues
29
watchers
9
size
0 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
3 minutes
Cold machine to finish
2 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
pnpm test exited 0, 164 passed; node dist/cli/index.js status confirmed bridge running on port 48765; node dist/cli/index.js --help lists all 13 commands
Model tokens used
27,422
Exact commit tested
a9f91cd98df1
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.

**Build**: `tsc -p tsconfig.json` completed with no errors, producing the `dist/` directory and the…
**Tests**: `vitest run` — 15 test files, 164 tests, all passed (3.34s test time).
**App launch**: `node dist/cli/index.js start` started the bridge on a random high port; `status` c…
No errors were encountered. No mocks were needed — the test suite and bridge run locally without th…
tokens used
27,422
All good. Here's the result summary.
**Install**: `pnpm install` and `pnpm build` succeeded. Node.js was v18 — upgraded to v22 via nvm (…
**Build**: `tsc -p tsconfig.json` completed with no errors, producing the `dist/` directory and the…
**Tests**: `vitest run` — 15 test files, 164 tests, all passed (3.34s test time).
**App launch**: `node dist/cli/index.js start` started the bridge on a random high port; `status` c…
No errors were encountered. No mocks were needed — the test suite and bridge run locally without th…

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 3.2 minutes, faster than the median of the 11 comparable projects Argusic has measured.
  • 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 2 times, so the result is not a one-off.

Of the 12 ai-agents projects Argusic has installed and timed, codex-with-chatgpt was the 5th fastest to reach a running state, and 8 of 12 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 3.2 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Did not run20.000.00
Argusic Runner1/3Runs100.000.01

Topics (from GitHub)

ai-agentschatgptcodexmcpmodel-context-protocoloauth

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/codex-with-chatgpt.svg)](https://argusic.com/subject/codex-with-chatgpt)

Questions

Does codex-with-chatgpt run?
Yes. codex-with-chatgpt runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test codex-with-chatgpt?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit a9f91cd98df1. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test codex-with-chatgpt?
The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does codex-with-chatgpt take to install?
3.2 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 codex-with-chatgpt need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing codex-with-chatgpt?
Nothing did, in the recorded run: zero errors between clone and running.
How does codex-with-chatgpt compare with the alternatives?
Of the 12 ai-agents projects Argusic has installed and timed, codex-with-chatgpt was the 5th fastest to reach a running state, and 8 of 12 reached one at all.
Where is the evidence for codex-with-chatgpt?
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