codex-slides

🎨 Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. ⚡ 10+ high-quality slides in ~4, 5 minutes, Fast mode renders every page in parallel. 🔍 Watch the whole chain live: research → outline → style → render → edit → present → export PDF/PPTX. 🖥️ Browser-first · zero API keys · durable projects.

Runssource: GitHubhomepageTypeScriptMITcommit dbc2a5992e93

TypeScript, MIT licensed. The project labels itself: agent skills, ai ppt, ai presentation, ai slides, codex, codex plugin, coding agents and deep research.

codex-slides runs. An Argusic agent installed it in 21 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Next.js web app builds with next build, all 67 unit tests pass, dev server serves homepage and 36 API routes on http://127.0.0.1:4311 returning HTTP 200, TypeScript typecheck passes, i18n check passes, MCP probe passes with 38 tools

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

At a glance

verdict
Runs
Argusic Score
97.5 / 100
cost of the verifying run
$0.08 (measured)
recorded runs
2
last tested
stars
992
forks
87
open issues
7
watchers
4
size
25 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 codex-slides, 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.

  • Test suite failed: all .test.mjs files importing .ts modules get ERR_UNKNOWN_FILE_EXTENSION5 minutes
  • Node.js 18 installed but project requires >=203 minutes
  • pnpm not installed2 minutes
  • check:browser-first fails with version assertion (plugin v0.1.0 vs package v0.2.1)
Install time
21 minutes
Cold machine to finish
10 minutes
Errors hit and fixed
4 hit, 4 fixed with no human help
How the result was proved
pnpm test: 67 passed, 0 failed; curl http://127.0.0.1:4311/ returned 200; curl /api/projects, /api/templates, /api/scenarios all returned 200; pnpm typecheck: tsc --noEmit exited 0; pnpm check:i18n: 3 locales, 977 source keys passed; MCP probe: 38 tools passed
Model tokens used
56,196
Exact commit tested
dbc2a5992e93
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 2, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

  "devDeps": [
    "@types/node",
    "@types/react",
    "@types/react-dom",
    "electron",
    "electron-builder",
    "tsx",
    "typescript"
  ]
}
tokens used
56,196

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.
  • Recovered from all 4 errors 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 did not, or is not known

  • Took 21 minutes to install, slower than the median of the 127 comparable projects Argusic has measured.

Of the 128 agent-skills projects Argusic has installed and timed, codex-slides was the 117th fastest to reach a running state, and 96 of 128 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.

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 Runner2/3Runs100.000.08
Argusic Runner1/3Runs95.000.06

Topics (from GitHub)

agent-skillsai-pptai-presentationai-slidescodexcodex-plugincoding-agentsdeep-researchdesign-systemgamma-alternativegenerative-aiimage-generationmcpnextjsopen-designpowerpointpptxpresentation-generatorslidestypescript

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-slides.svg)](https://argusic.com/subject/codex-slides)

Questions

Does codex-slides run?
Yes. codex-slides runs. Argusic installed and launched it on a clean machine in 21 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test codex-slides?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit dbc2a5992e93. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test codex-slides?
The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does codex-slides take to install?
21 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-slides need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing codex-slides?
4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does codex-slides compare with the alternatives?
Of the 128 agent-skills projects Argusic has installed and timed, codex-slides was the 117th fastest to reach a running state, and 96 of 128 reached one at all.
Where is the evidence for codex-slides?
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