JinaClip
Professional-grade, local-first browser extension that transforms any webpage into high-fidelity, LLM-friendly Markdown entirely within the browser's runtime. Zero-cloud, privacy-centric, and designed specifically for AI workflows.
Runssource: GitHubJavaScriptMITcommit ebeb621ce49e
JavaScript, MIT licensed. The project labels itself: ai workflows, browser extension, chrome extension , clipboard api, dom parsing, es6, jina ai jina reader and llm friendly.
JinaClip runs. An Argusic agent installed it in 11 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
npm install completes (engine warnings for Node 18), npm run build creates dist/, npm test passes 12/12 engine core tests, Chrome extension loads via puppeteer with service worker active and engine extracts metadata/markdown correctly from real pages.
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 60 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.
- No tests existed8 minutes
- ESLint 10 requires Node >=20 (container has Node 18)2 minutes
- jsdom 31 requires Node >=221 minute
- Install time
- 11 minutes
- Cold machine to finish
- 15 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- Puppeteer loaded dist/ as unpacked extension, verified service worker URL has correct manifest, and page.evaluate() ran the _engineCoreBody on a test HTML page producing correct title/description/author/h1/bold/link extraction. npm test: 12/12 passed.
- Model tokens used
- 229,576
- Exact commit tested
- ebeb621ce49e
- 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.
2. **`npm run build`** — compiles `dist/` folder. Success. 3. **`npm test`** — no tests existed. I wrote 12 unit tests that extract the `_engineCoreBody` func… 4. **Real Chrome integration test** — using puppeteer 21 with Chrome 115, I loaded the `dist/` fold… - The service worker starts and has the correct manifest - The engine injects into a page and correctly extracts title, description, author, and converts… ### Errors encountered | Error | Fix | |---|---| | ESLint 10 requires Node >=20; `util.styleText is not a function` | Downgraded to [email protected] | | jsdom 31 requires Node >=22 | Downgraded to jsdom@24 | | No tests existed | Added 12-unit Jest test suite | | `innerText` not implemented in jsdom | Added polyfill in test harness |
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 11 minutes.
- Recovered from all 3 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 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.13 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.01 |
Topics (from GitHub)
ai-workflowsbrowser-extensionchrome-extension-clipboard-apidom-parsinges6jina-ai-jina-readerllm-friendlylocal-firstmarkdown-convertermv3privacy-centricproductivity-toolshadow-domweb-scraper
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/jinaclip)Questions
- Does JinaClip run?
- Yes. JinaClip runs. Argusic installed and launched it on a clean machine in 11 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test JinaClip?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ebeb621ce49e. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test JinaClip?
- The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does JinaClip 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 JinaClip need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing JinaClip?
- 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.
- Where is the evidence for JinaClip?
- 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.