Codex-X
OpenAI Codex 桌面端/CLI 的可视化管理工具，具有Provider/API 切换、会话同步、提示词注入、Skills/MCP 管理、TOML 配置可视化的跨平台工具。
Runs with mockssource: GitHubhomepageRustMITcommit 8f018fddd3ee
Rust, MIT licensed.
Codex-X runs, with stand-ins for the services it depends on. An Argusic agent installed it in 14 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The frontend builds and serves correctly on port 1420 (200 OK); all 79 unit tests pass using mocked Tauri IPC, covering update controller, config health monitor, provider presets/settings, routing, session identity, and usage statistics modules.
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, 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.
- Rust/Cargo not installed2 minutes
- Node.js 18 too old for Vite 7 build (crypto.hash not a function)2 minutes
- pnpm not installed1 minute
- Tests import .ts files which Node.js 18 can't load natively1 minute
- Tauri Rust backend build fails — missing system libraries glib-2.0.pc, gtk-3, webkit2gtk, etc.
- Install time
- 14 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- node --test --import tsx tests/*.test.mjs: 79 tests passed, 0 failed; curl -s -o /dev/null -w %{http_code} http://127.0.0.1:1420/ returned 200
- Model tokens used
- 74,825
- Exact commit tested
- 8f018fddd3ee
- 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.
test/worker.test.js:2:import { createHmac } from "node:crypto";
The star-history-worker has pre-existing test issues (crypto namespace requires newer Node.js). Thi…
Now let me compile the final report. Here's what I've accomplished:
exec
/bin/sh -lc 'cd /work/repo/apps/desktop && export PATH="/tmp/node-v22.14.0-linux-x64/bin:$HOME/.npm…
succeeded in 3251ms:
v22.14.0
Here is the full picture of what was done.
2026-10-02T13:21:54.178257Z ERROR codex_core::session: failed to record rollout items: thread 01a0f…
tokens used
74,825
Here is the full picture of what was done.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 14 minutes, faster than the median of the 8 comparable projects Argusic has measured.
- Recovered from all 5 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.
Of the 9 Rust projects Argusic has installed and timed, Codex-X was the 4th fastest to reach a running state, and 8 of 9 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.05 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/codex-x)Questions
- Does Codex-X run?
- Codex-X runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 14 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test Codex-X?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8f018fddd3ee. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Codex-X?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Codex-X take to install?
- 14 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-X need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Codex-X?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Codex-X compare with the alternatives?
- Of the 9 Rust projects Argusic has installed and timed, Codex-X was the 4th fastest to reach a running state, and 8 of 9 reached one at all.
- Where is the evidence for Codex-X?
- 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.