Orkas-VideoStudio

Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.

Runssource: GitHubhomepageTypeScriptMITcommit c0c3c3eac359

TypeScript, MIT licensed. The project labels itself: ai agents, ai video, cli, coding agents, ffmpeg, generative ai, hyperframes and local first.

Orkas-VideoStudio runs. An Argusic agent installed it in 11 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 repository installs, builds, typechecks, benchmarks, and passes all 282 unit tests plus 47 E2E tests including a real three-scene video production pipeline that composes HTML motion graphics, renders via HyperFrames 0.7.60 with chrome-headless-shell, burns captions with ffmpeg, and passes the delivery promise-check guard, producing a verified 1920x1080 h264+aac 9.1s MP4 with audible audio in all three scenes and...

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
$0.20 (measured)
recorded runs
1
last tested
stars
345
forks
28
open issues
0
watchers
5
size
1 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 Orkas-VideoStudio, 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.

  • Node v18.19.1 below required >=224 minutes
  • Build scripts blocked for esbuild/onnxruntime-node/sharp2 minutes
  • chrome-headless-shell zip extraction failed (no unzip/yauzl)2 minutes
  • pnpm not found1 minute
  • E2E test failed on unclassified [SystemMemory] stderr lines1 minute
Install time
11 minutes
Cold machine to finish
12 minutes
Errors hit and fixed
5 hit, 5 fixed with no human help
How the result was proved
pnpm test exited 0, 282 passed; pnpm test:video:e2e exited 0, 47 passed including full production pipeline; ffmpeg -v error -i video.mp4 -f null - returned clean decode
Model tokens used
129,130
Exact commit tested
c0c3c3eac359
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 1, 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.

129,130
All tasks complete. Here's the final report:
**Install & dependencies**: Node upgraded v18→v22 via `n`; pnpm installed globally; all deps instal…
**Build**: All 5 workspace packages built successfully (`tsc`).
**Tests**: `pnpm test` — 282 passed, 12 skipped (25 files passed, 2 skipped). `pnpm typecheck` — pa…
**E2E video production**: All 47 tests passed including the three-scene composition→draft→burned ca…
**Errors encountered & fixed**:
1. Node v18 required >=22 — installed Node 22 via `n`
2. pnpm not in PATH — installed globally, added `~/.node/bin` and `~/.npm-global/bin` to PATH
3. Builds blocked for esbuild/onnxruntime-node/sharp — added `approvedBuilds` and `onlyBuiltDepende…
4. chrome-headless-shell extraction failed (no `unzip`/`yauzl`) — extracted with Python `zipfile` m…
5. E2E test stderr check failed on `[SystemMemory]` lines from HyperFrames — patched the test to ac…

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 5 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.

What did not, or is not known

  • Took 11 minutes to install, slower than the median of the 116 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 117 ai-agents projects Argusic has installed and timed, Orkas-VideoStudio was the 80th fastest to reach a running state, and 87 of 117 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 Runner1/3Runs100.000.20

Topics (from GitHub)

ai-agentsai-videoclicoding-agentsffmpeggenerative-aihyperframeslocal-firstmcp-servermotion-graphicsopen-sourcesubtitlestext-to-videottstypescriptvideo-automationvideo-compositionvideo-editingvideo-generationwhisper-cpp

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/Orkas-VideoStudio.svg)](https://argusic.com/subject/orkas-videostudio)

Questions

Does Orkas-VideoStudio run?
Yes. Orkas-VideoStudio runs. Argusic installed and launched it on a clean machine in 11 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test Orkas-VideoStudio?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit c0c3c3eac359. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test Orkas-VideoStudio?
The run that produced this verdict cost $0.20: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Orkas-VideoStudio take to install?
11 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 Orkas-VideoStudio need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Orkas-VideoStudio?
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 Orkas-VideoStudio compare with the alternatives?
Of the 117 ai-agents projects Argusic has installed and timed, Orkas-VideoStudio was the 80th fastest to reach a running state, and 87 of 117 reached one at all.
Where is the evidence for Orkas-VideoStudio?
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.

Discussion