User repository on GitHub
Testing Jev AI with SeleniumBase
- Forks
- 1
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Jev Testing
A small SeleniumBase project that sends a page's reduced HTML to Jev and gets back three structured answers: whether a CAPTCHA is present, a 0-100 confidence score and which of six types it is. The README warns scores vary between runs and are not calibrated probabilities.
- Stars
- 3
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- mdmintz
- Last verified
- Oct 2026
- Languages
- Python
- Capabilities
- Open sourceRequires API key
Highlights
- Three structured results per page: CAPTCHA yes/no, a 0-100 confidence score, and one of six types from Cloudflare Turnstile to Friendly CAPTCHA.
- The script opens each URL with SeleniumBase CDP, waits 1.5 seconds, reduces the HTML to CAPTCHA evidence and sends that to Jev.
- A sample run found Friendly CAPTCHA, Cloudflare Turnstile, DataDome Slider, Google reCAPTCHA and hCaptcha with scores from 87 to 99.
- The README warns scores may vary between runs and are ordinal confidence ratings, not calibrated probabilities.
- Setup is three steps: install requirements.txt, export TYPESAFE_API_KEY, then run python seleniumbase_jev.py.
Quickstart
bash
python -m pip install -r requirements.txt
export TYPESAFE_API_KEY="YOUR_API_KEY_HERE"
python seleniumbase_jev.pyWatch out
README and GitHub metadata reviewed 2026-10-17; the sample output is illustrative, a No answer only means Jev found insufficient evidence in the supplied HTML, dynamically injected CAPTCHAs may be missed, and no accuracy evaluation is published.
Questions about this entry
Short answers drawn from the linked project or page.
A small open-source project that tests Jev with SeleniumBase by identifying the presence of CAPTCHAs. It opens each URL, captures the page HTML, reduces it to CAPTCHA-related evidence and asks Jev to analyze it.
Three structured answers: captcha_detected as Yes or No, a score from 0 to 100, and captcha_type as one of Cloudflare Turnstile, Google reCAPTCHA, hCaptcha, DataDome Slider, Friendly CAPTCHA or Other CAPTCHA; captcha_type is None when the answer is No.
Install the Python requirements with python -m pip install -r requirements.txt, export TYPESAFE_API_KEY with your key, then run python seleniumbase_jev.py. Keep the key private and do not commit it to your repository.
It is derived from Jev's ordinal confidence rating and indicates confidence in the detection decision. The README says scores may vary between runs and must not be interpreted as calibrated probabilities.
SeleniumBase CDP opens the page, waits 1.5 seconds and retrieves the HTML; the script reduces it to CAPTCHA-related evidence, keeping all script and iframe tags plus elements and text containing CAPTCHA keywords. Pages with many scripts can still produce large input.
Detection depends on the HTML evidence available when the page is inspected; a CAPTCHA integration may exist even when no challenge is visible, dynamically injected elements may be missed, and a No result does not guarantee that the page has no CAPTCHA.
The GitHub user mdmintz publishes it under the MIT license; the repository was created 2026-10-13. The README lists no affiliation with TypeSafe or SeleniumBase beyond using their tools.
More Jev resources like this
Eleven small runnable projects for learning Jev and other System One decision models, each lesson pairing a one-command web demo with a whiteboard and README, from the three question types through jobs sorting and contract review to Jev inside a SQL query. Every demo makes live API calls.
Jev Demos & Experiments#community#github#python
Community
aianytime/jev-crash-coursePython
aianytime/jev-crash-coursePythonFive self-contained Jev demos, one folder each: Jev fetching for Claude, Jev and Laya grading 500 AI answers, a prompt-injection review gate, and two fine-tuned decider comparisons against Jev.
Jev Demos & Experiments#community#python#demos
Community
mani-aiml/jev-demosPython
mani-aiml/jev-demosPythonA small Python app that asks whether a headline is Onion-style satire or real news. Jev runs through TypeSafe's API with your own key and is compared side by side with AnyJev L0 and raw Qwen3-8B running locally, with an option to swap the answer order.
Jev Demos & Experiments#community#github#python
Community
andrisgauracs/onion-or-notPython
andrisgauracs/onion-or-notPythonA beginner-friendly RAG app that answers questions about your documents using only what is written there: rag.py finds the right chunks, asks Jev to check them and gets the answer from OpenAI, while a Streamlit page shows the result with Jev's scores.
Jev Demos & Experiments#community#github#python
Two Jev demos over SprintPulse QA data: one scores release risk with a 10-level rubric evaluated against a reference score, the other diagnoses the main risk cause with a 9-label choice question, both sending the same per-ticket signals to Jev's System One API.
Jev Demos & Experiments#community#github#python
Community
avi350751/jev-qa-analyzerPython
avi350751/jev-qa-analyzerPythonFinds Dublin buses that are scheduled, due, and just not there: it checks the GTFS timetable against the live vehicle feed and flags trips with no bus and no cancellation. Built in a day for Build for Ireland, live on open data and Jev.
Jev Demos & Experiments#community#github#transit
Community
Rajatgdev/Ghost_busPython
Rajatgdev/Ghost_busPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.