ONNXAgent

Runs exported checkpoints through ONNX Runtime with prediction, batching, long-document, and structured-decision APIs.

Parent repository GitHub

Type: module
Repository: NandhaKishorM/laya
Readiness: Usable for evaluation and carefully validated deployments, but shipped calibration, multilingual task quality, option-order sensitivity, and workload-specific accuracy require local testing before automated actions.
Keywords: 5

Location

Repository path

README.md

Invocation

ONNXAgent.predict_batch(...); ONNXAgent.predict_long(...); ONNXAgent.decide_batch(...)

Setup

Installation / activation

Python API call with an ONNX export

Keywords

ONNXONNX Runtimebatchpredict_longdecide_batch

Repository context

NandhaKishorM/laya

Apache-2.0 multilingual decision-model toolkit that provides Python and TypeScript SDKs, local CLI and HTTP serving, ONNX runtimes, framework integrations, evaluation harnesses, and an optional MCP server for fast typed choice, ordinal-score, and yes/no decisions; no native Claude Code plugin, hook, skill, or Claude-specific installation path is evidenced.

machine learningnatural language processingclassificationdecision routingmultilingual inferenceguardrailscontent moderationsupport automationmodel routingevaluation

Open full repository research