WeftCut
Free, open-source AI video editor for macOS, Windows and Linux, drive the whole timeline from any MCP client.
Runssource: GitHubhomepageTypeScriptMITcommit 610061dca1e9
TypeScript, MIT licensed. The project labels itself: ai agent, ai video editor, claude, cross platform, desktop app, electron, ffmpeg and llm.
WeftCut runs. An Argusic agent installed it in 31 minutes and hit 8 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
WeftCut v0.4.0 builds successfully on Linux x64: both napi addons compiled (@weftcut/core exports 17 symbols, @weftcut/native-decode compiled with ffmpeg-lgpl), ffmpeg and ffmpeg-lgpl resources staged, vitest suite runs 9284 of 9288 tests passing, all 20 Rust eval-crate tests pass, 99 of 100 script tests pass.
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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Node.js v18.19.1 too old (requires >=24)3 minutes
- napi:build:decode failed - libclang not found3 minutes
- clang bindgen failed - limits.h not found3 minutes
- Rust toolchain not installed2 minutes
- npmrc ignore-scripts=true blocked optional native bindings1 minute
- ffmpeg-sys-next build failed - libavutil.pc not found1 minute
- Install time
- 31 minutes
- Cold machine to finish
- 31 minutes
- Errors hit and fixed
- 8 hit, 8 fixed with no human help
- How the result was proved
- npm test --workspace apps/desktop: 9284 passed, 1 failed; cargo test in native/eval: 20 passed; node -e 'require("native/index.linux-x64-gnu.node")' loads and exports 17 symbols
- Model tokens used
- 157,699
- Exact commit tested
- 610061dca1e9
- 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.
4. **napi:build:decode failed** multiple times: - `libclang` not found → extracted from apt `.deb` packages (libclang1-18, libllvm18), set `LIBC… - `ffmpeg-sys-next` couldn't find `libavutil.pc` → set `PKG_CONFIG_PATH` to ffmpeg-lgpl's pkgcon… - Clang couldn't find `limits.h` → extracted `libclang-common-18-dev` headers, set `C_INCLUDE_PA… 5. **1 pre-existing vitest failure** (`rmSync` on symlinked dir — Node 24 behavior) 6. **1 pre-existing script test failure** (Playwright Chromium not installed) **What was verified:** - `npm test`: 9284 passed, 1 failed (pre-existing), 3 skipped - `cargo test` (eval crate): 20 passed - `npm run test:scripts`: 99 passed, 1 failed (Playwright Chromium not installed) - Core napi addon loads and exports 17 symbols - Both napi addons built and co-located with ffmpeg-lgpl shared libs
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 8 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 31 minutes to install, slower than the median of the 58 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 59 ai-agent projects Argusic has installed and timed, WeftCut was the 55th fastest to reach a running state, and 33 of 59 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
Topics (from GitHub)
ai-agentai-video-editorclaudecross-platformdesktop-appelectronffmpegllmmcpmcp-servermodel-context-protocolnlenon-linear-editorpixijsrusttypescriptvideovideo-editingvideo-editorwebcodecs
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/weftcut)Questions
- Does WeftCut run?
- Yes. WeftCut runs. Argusic installed and launched it on a clean machine in 31 minutes, hitting 8 errors on the way, and recorded the session.
- How did Argusic test WeftCut?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 610061dca1e9. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test WeftCut?
- The run that produced this verdict cost $0.45: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does WeftCut take to install?
- 31 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 WeftCut need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing WeftCut?
- 8 things broke in the recorded run, and 8 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does WeftCut compare with the alternatives?
- Of the 59 ai-agent projects Argusic has installed and timed, WeftCut was the 55th fastest to reach a running state, and 33 of 59 reached one at all.
- Where is the evidence for WeftCut?
- 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.