jev-edge English | 简体中文 Typed-judgment admission control at the traffic edge. jev-edge sits in nginx / OpenResty or Apache APISIX, behind Envoy, Istio, HAProxy, Traefik, Caddy and plain nginx, in a Cloudflare Worker, a Next.js or Node middleware or Lambda@Edge, or inside LiteLLM proxy, and asks one question about incoming requests: what is this request trying to do to my service? It uses TypeSafe Jev, a System One model that returns probabilities instead of prose, to catch prompt injection and abuse at the entry point of LLM-backed applications, before the request reaches your backend.
| Stars | 41 |
| Forks | 1 |
| Language | Lua |
| Category | AI Tool |
| License | Apache-2.0 |
| Quality Score | 66.4167066552218/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-06 |
| Created | 2026-09-21 |
| Est. Tokens | ~23k |
Explore other popular ai tool tools:
jev-edge is Typed-judgment admission control at the traffic edge: three-layer prompt-injection and abuse filter for nginx/OpenResty, powered by TypeSafe Jev. Fail-open, cached, hot-reloadable.. It is categorized as a AI Tool with 41 GitHub stars.
jev-edge is primarily written in Lua. It covers topics such as api-gateway, ext-authz, jev.
You can find installation instructions and usage details in the jev-edge GitHub repository at github.com/kiwi0719/jev-edge. The project has 41 stars and 1 forks, indicating an active community.
jev-edge is released under the Apache-2.0 license, making it free to use and modify according to the license terms.