agent-fetch
Full-content web fetcher for AI agents, Chrome TLS fingerprinting, browser impersonation, multi-strategy article extraction, and web scraping.
Runssource: GitHubhomepageTypeScriptMITcommit 7632d139d5df
TypeScript, MIT licensed. The project labels itself: ai agent skill, ai agents, anti bot detection, browser impersonation, content extraction, fetcher, html to markdown and httpcloak.
agent-fetch runs. An Argusic agent installed it in 3.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
agent-fetch 0.1.6 builds from source, passes all 904 unit tests, and successfully fetches and extracts real web pages (Wikipedia, example.com) via CLI.
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, 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 in container incompatible with project engine requirement (>=20). npm install warned EBADENGINE for vitest; 13 test files failed with ReferenceError (File, DOMMatrix not defined).3 minutes
- Install time
- 4 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm test exited 0, 904 passed (34 files). npx agent-fetch --json https://en.wikipedia.org/wiki/Node.js returned success:true with full extracted HTML (title='Node.js', 534ms). npx agent-fetch --raw https://example.com returned complete HTML. npx agent-fetch --version returned 'agent-fetch 0.1.6'.
- Model tokens used
- 41,124
- Exact commit tested
- 7632d139d5df
- 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.
**Error 1 — Node.js version mismatch** The container has Node.js v18.19.1 but the project requires `>=20.0.0`. With v18, `npm install` iss… **Fix:** Downloaded Node.js v22.23.4 binary to `/tmp/node-v22.23.4-linux-x64/bin/node`, re-ran `npm… All four quality gates pass with Node.js v22: - **`npm run build`** → exit 0, `tsc` completes - **`npm run lint`** → exit 0 - **`npm run format:check`** → "All matched files use Prettier code style!" - **`npm test`** → 904 tests pass across 34 files, all green **Real-world verification:** `npx agent-fetch --json https://en.wikipedia.org/wiki/Node.js` returne… No mocks were needed — the app works against live sites with zero configuration. No third-party API… ```json ```
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 3.5 minutes.
- Recovered from all 1 error 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.
- A quick evaluation: it was running 3.5 minutes after the clone.
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 | 0.03 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.03 |
Topics (from GitHub)
ai-agent-skillai-agentsanti-bot-detectionbrowser-impersonationcontent-extractionfetcherhtml-to-markdownhttpcloaknodejspdf-extractionreadabilitytls-fingerprinttypescriptweb-content-extractionweb-crawlerweb-fetcherweb-scraping
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agent-fetch)Questions
- Does agent-fetch run?
- Yes. agent-fetch runs. Argusic installed and launched it on a clean machine in 4 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test agent-fetch?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7632d139d5df. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test agent-fetch?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agent-fetch take to install?
- 3.5 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 agent-fetch need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agent-fetch?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for agent-fetch?
- 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.