devwithjevLinkGuard Classifies Links Before Clicks
LinkGuard uses Jev to classify links as Safe, Suspicious, or Scam and provide a confidence score. It takes a URL, anchor text, and page title as inputs.
Jetwani Avinash@jetwaniavinash๐
Jev doesn't explain. It decides. I hand it a URL, the anchor text and the page title. It hands back Safe / Suspicious / Scam + confidence in ~0.5s โ in 98 output tokens. Fast enough to run on hover, not after the click. So I built LinkGuard ๐ก๏ธ : https://t.co/IPVzYKA9vN @typesafeai
The author says it responds in ~0.5s using 98 output tokens, making it fast enough to run on hover rather than after a click.
Also filed under Tools & apps
- Jev Auth Event Auditing and Alert Telemetry
It provides shadow-mode Jev authn/authz event auditing and alert telemetry for OAuth2 and IAM.
- Ask Questions About Git History
HekaJev lets users ask questions about Git history in plain English. The open-source tool is built using Jev.
- Local Jev-Compatible Decision-Model Runner
ollaya is a local decision-model runner with a Jev-compatible System One API.
- Open Jev-Style Decision Model
JevAny is an open Jev-style model and training stack for typed decisions and option probabilities.