codex-chatgpt-web
Use ChatGPT Web (including Pro) as a native model in Codex, with context, tools, streaming and images, without using Codex quota.
Runs with mockssource: GitHubTypeScriptMITcommit a13cd0995096
TypeScript, MIT licensed. The project labels itself: chatgpt, chatgpt pro, codex, free ai, mcp, openai, playwright and quickstart.
codex-chatgpt-web runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1.5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
codex-chatgpt-web 6.1.1 installs, builds, typechecks, and passes 155/155 tests on Bun 1.4.2; CLI commands respond correctly; full browser-based operation requires ChatGPT setup step
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 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. 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.
- Bun not installed in container - requires unzip which needs root1 minute
- package.json pinned [email protected] but installed [email protected]; verify script rejected mismatched versions0.5 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 7 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- bun test ./tests exited with 155 pass, 1 skip (intentional), 0 fail across 31 files; bun run typecheck exited 0; bun run src/cli.ts --help returned usage text
- Model tokens used
- 128,926
- Exact commit tested
- a13cd0995096
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- Updated `package.json` `packageManager`, `@types/bun`, and `engines.bun` from 1.4.0 → 1.4.2 - Updated README Bun version references from 1.4.0 → 1.4.2 in 4 locale files **Cosmetic issues (no functional impact):** `verify` script fails on release-version strings in CI/… tokens used 128,926 All systems verified. Here's the final report: **Verified status:** `bun install` completed, typecheck passes with 0 errors, 155 tests pass / 0 fa… **Fixed during setup:** - Bun 1.4.2 installed via `npm install bun` (container had no Bun; `curl | bash` required `unzip` w… - Updated `package.json` `packageManager`, `@types/bun`, and `engines.bun` from 1.4.0 → 1.4.2 - Updated README Bun version references from 1.4.0 → 1.4.2 in 4 locale files **Cosmetic issues (no functional impact):** `verify` script fails on release-version strings in CI/…
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
- Installed in 1.5 minutes.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
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 | 1/3 | Runs with mocks | 92.00 | 0.03 |
Topics (from GitHub)
chatgptchatgpt-procodexfree-aimcpopenaiplaywrightquickstartresponses-apitypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/codex-chatgpt-web)Questions
- Does codex-chatgpt-web run?
- codex-chatgpt-web runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test codex-chatgpt-web?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a13cd0995096. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test codex-chatgpt-web?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does codex-chatgpt-web take to install?
- 1.5 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 codex-chatgpt-web need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing codex-chatgpt-web?
- 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 codex-chatgpt-web?
- 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.