examples

Examples for using Hyperbrowser

Runs with mockssource: GitHubhomepageTypeScriptMITcommit 742df66242aa

TypeScript, MIT licensed. The project labels itself: examples, scraping, web and web scraping.

examples runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.2 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

After npm install, TypeScript compiles cleanly and the company-researcher CLI runs end-to-end against a schema-correct local Hyperbrowser mock, producing the full structured research output and exiting 0; real Hyperbrowser/OpenAI API keys were not exercised.

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

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.12 (measured)
recorded runs
1
last tested
stars
241
forks
38
open issues
1
watchers
2
size
6 MB
created
last push

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.

Time lost to each failure while testing examples, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • The quick-start CLI (company-researcher.ts) is readline/TTY-only; piping stdin made it print the two prompts then exit code 0 before ever calling Hyperbrowser, so it could not be exercised non-interactively.1 minute
  • The app had no way to target a non-default API endpoint, so it could not be pointed at a local mock to verify end-to-end without real credentials.1 minute
Install time
under a minute
Cold machine to finish
12 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
npm install (exit 0, 61 packages) and npx tsc --noEmit (exit 0) passed; python3 run_test2.py started a local schema-correct Hyperbrowser mock on 127.0.0.1:8123 and drove npx ts-node company-researcher.ts in a PTY, which printed the two prompts, sent answers, and rendered the full result (RESEARCH RESULTS FOR: ACME CORP, OVERVIEW, 3 KEY POINTS, ADDITIONAL INFORMATION) then exited 0; the mock request log confirmed POST /api/extract with x-api-key mock-test-key-123 and the JSON-schema'd body, followed by GET /api/extract/mock-job-1/status and GET /api/extract/mock-job-1.
Model tokens used
370,835
Exact commit tested
742df66242aa
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of one of the attempts below. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

exec
/bin/sh -lc "python3 -c \"import json; s=open('/tmp/result.txt').read().split('ARGUSIC_RESULT: ',1)…
 succeeded in 0ms:
JSON OK; keys: ['install_succeeded', 'launch_succeeded', 'install_minutes', 'errors', 'test_depth',…
Everything is verified and the report JSON is valid.
exec
/bin/sh -lc 'cat /tmp/result.txt' in /work/repo
 succeeded in 0ms:
Done. Here is the report line.
tokens used
370,835
Done. Here is the report line.

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 0.2 minutes.
  • Recovered from all 2 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.

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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks92.000.12

Topics (from GitHub)

examplesscrapingwebweb-scraping

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/examples.svg)](https://argusic.com/subject/examples)

Questions

Does examples run?
examples runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 0 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test examples?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 742df66242aa. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test examples?
The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does examples take to install?
0.2 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 examples need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing examples?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for examples?
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.

Discussion