velocut
AI-native, local-first video editor by Ribbi, runs entirely in the browser. Rust/WASM engine, WebGPU compositing, WebCodecs export; humans and LLM agents edit through the same JSON command protocol.
Runssource: GitHubhomepageTypeScriptMITcommit 959857c624f2
TypeScript, MIT licensed. The project labels itself: ai, ai agent, browser, claude, llm, local first, rust and typescript.
velocut runs. An Argusic agent installed it in 3 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
Velocut is fully operational: the TypeScript reference engine runs under Vite with all 62 unit tests and both Playwright E2E journeys passing, the Rust golden-vector test suite passes, and the WASM canonical engine compiles and drops into the editor's public directory.
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
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
- 7 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- npm test passed 62/62; cargo test passed 1/1 golden vectors; npx playwright test passed 2/2 (boot/import/edit/persist/reload + project isolation); dev server responded HTTP 200; wasm-pack build succeeded
- Model tokens used
- 52,808
- Exact commit tested
- 959857c624f2
- 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.
52,808 All systems verified successfully. Here is the final report: **Summary of what was done:** - **Node**: Installed nvm, upgraded from Node v18 to v22.23.2 (required >=22.6) - **Rust toolchain**: Installed rustup, Rust 1.98.1, wasm-pack 0.15.0, wasm32-unknown-unknown target - **Web deps**: `npm install` succeeded - **TS unit tests**: 62/62 passed (golden vectors + agent SDK + scene SDK) - **Rust tests**: 1/1 golden vector passed, clippy clean, fmt perfect - **WASM engine**: Built successfully (418KB wasm binary) - **Dev server**: Starts, responds HTTP 200, serves HTML - **Playwright E2E**: 2/2 passed — boots with engine, imports media, edits, persists across reload,… No errors were encountered at any step.
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 minutes, faster than the median of the 36 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 37 ai projects Argusic has installed and timed, velocut was the 11th fastest to reach a running state, and 30 of 37 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 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
Topics (from GitHub)
aiai-agentbrowserclaudellmlocal-firstrusttypescriptvideo-editingvideo-editorwasmwebassemblywebcodecswebgpu
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/velocut)Questions
- Does velocut run?
- Yes. velocut 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 velocut?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 959857c624f2. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test velocut?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does velocut take to install?
- 3 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 velocut need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing velocut?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does velocut compare with the alternatives?
- Of the 37 ai projects Argusic has installed and timed, velocut was the 11th fastest to reach a running state, and 30 of 37 reached one at all.
- Where is the evidence for velocut?
- 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.