znyx-runtime is an open-source FastAPI-based runtime for evaluating large language model (LLM) traffic against defined safety and policy guardrails. It provides rules-based enforcement out of the box and can integrate with a Znyx inference sidecar for machine learning-based evaluation. Designed for AI developers and platform engineers to ensure safe and compliant LLM deployments.
In the AI security & guardrails space, znyx-runtime takes a focused approach. It focuses on ensuring LLM outputs comply with safety and policy guardrails in AI applications. It is built as an open-source project for AI developers and platform engineers. znyx-runtime is open source under the Apache-2.0 license. It ships for the command line and API, and it can be self-hosted.
zitrino-oss builds and maintains znyx-runtime, and it first shipped in 2026. Development happens publicly on GitHub with 22 commits in the last 90 days. Among its 5 catalogued features are policy evaluation, LLM traffic analysis, and fastAPI service.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do