Ollaya: pull and serve open decision models locally

A local daemon and CLI for downloading and running open decision models behind a TypeSafe-compatible API. It includes an MCP interface and model definitions for typed Choice, Score and Noul workflows.

Notes

Existing Jev clients can target its /v1/systemone endpoint through a base-URL change. The runtime supports ONNX CPU/CUDA execution and GGUF models on llama.cpp with CPU, CUDA or Apple Metal.

source-backed — Public repository, docs or live artifact. About this label

Destinations

Filed under

• #local-models
• #runtime
• #mcp
• #open-source

In collections

• Local & replica models →