Skip to content
NNRP - Neural Network Runtime Protocol

Neural Network Runtime Protocol

Real-time AI Runtime Protocol

NNRP is a domain-level application protocol for AI model calls, streaming results, cache bindings, and session migration. It moves runtime cooperation semantics into the protocol layer so SDKs, conformance suites, and cloud runtime integrations can evolve around the same contract.

ProtocolOverview

Start from the background, boundaries, core objects, and version entry points.

ConformanceShared Test Suite

Read capability manifests, CI integration, and version-selection rules.

SDKLanguage SDKs

Open quick starts and API references for Python, C#, Rust, and more.

NNRP Documentation