oh-my-cassette
你的随身 AI 剪辑搭档 | Pocket AI co-editor for video montage, AI video editing plugin & MCP server for Claude Code, Codex, Hermes & OpenCode
Runs with mockssource: GitHubPythonMITcommit fd19f89353d7
Python, MIT licensed. The project labels itself: agent, agent skills, ai agent, ai video editing, chat to edit, claude code, claude code plugin and claude code skills.
oh-my-cassette runs, with stand-ins for the services it depends on. An Argusic agent installed it in 2 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The packaged oh-my-cassette 0.6.0 installs and runs: it answers --version and --help, starts as a stdio bridge that lists the reference service's tools, imports and uploads real ffmpeg transcodes that decode cleanly, downloads the declared export, and the test suite reports 184 passed and 2 skipped.
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. 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.
- uv was not on PATH and `pip install --user uv` was rejected with an externally-managed-environment (PEP 668) error3 minutes
- uv.lock still locked oh-my-cassette 0.5.0 and `uv lock --check` reported the lockfile needs updating3 minutes
- llms-install.md claimed `uvx oh-my-cassette==0.6.0 --version` prints `oh-my-cassette 0.5.0`, but it printed 0.6.02 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- `uv run pytest -rs` exited 0 with 184 passed, 2 skipped; `uvx oh-my-cassette==0.6.0 check --url http://127.0.0.1:8790/mcp --upload` exited 0 with 8 passed, 0 failed; a stdio client launching `uvx oh-my-cassette==0.6.0` listed 7 tools and returned import ref `media:71f91101cdd8b5f5` and export path `/tmp/e2e-ws/cassette-exports/cut.mp4`; `ffmpeg -v error -i` on both transcoded renditions exited 0; `uv build` produced oh_my_cassette-0.6.0 wheel and sdist
- Model tokens used
- 125,517
- Exact commit tested
- fd19f89353d7
- 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.
I verified the install, the CLI, the stdio bridge, the media pipeline, and the test suite, and fixe… **What I fixed** - `llms-install.md`:69 claimed `--version` prints `oh-my-cassette 0.5.0`; it prints `0.6.0`. Correc… - `uv.lock` was stale, still locking `oh-my-cassette 0.5.0`; `uv lock --check` failed. Regenerated … - `uv` was absent from the container. Installed it to the user site (PEP 668 blocked the plain user… **What I verified** - `uvx oh-my-cassette==0.6.0 --version` → `oh-my-cassette 0.6.0`. - `uv run pytest -rs` → 184 passed, 2 skipped in 61.72s, exit 0. - `uvx ... check --upload` against a standalone schema-correct reference service → 8 passed, 0 fail… - A stdio session through the installed `uvx` binary listed 7 tools, imported a real MP4, and downl… - `uv build` produced the 0.6.0 wheel and sdist; `ruff check .` passed. - The real upstream answered `401 unauthorized` without a token, so the live tests were skipped as …
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 2 minutes, faster than the median of the 133 comparable projects Argusic has measured.
- Recovered from all 3 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 134 agent projects Argusic has installed and timed, oh-my-cassette was the 27th fastest to reach a running state, and 86 of 134 reached one at all.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.11 |
Topics (from GitHub)
agentagent-skillsai-agentai-video-editingchat-to-editclaude-codeclaude-code-pluginclaude-code-skillscodexffmpeghermes-agentllmmcpmcp-servermcp-toolsopencodepythonvideo-editingvideo-editorvideo-montage
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/oh-my-cassette)Questions
- Does oh-my-cassette run?
- oh-my-cassette runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test oh-my-cassette?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit fd19f89353d7. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test oh-my-cassette?
- The run that produced this verdict cost $0.11: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does oh-my-cassette take to install?
- 2 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 oh-my-cassette need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing oh-my-cassette?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does oh-my-cassette compare with the alternatives?
- Of the 134 agent projects Argusic has installed and timed, oh-my-cassette was the 27th fastest to reach a running state, and 86 of 134 reached one at all.
- Where is the evidence for oh-my-cassette?
- 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.