Ollaya runs open decision models on your own machine the way Ollama runs LLMs: one binary, with `run`, `pull`, `list`, `ps`, `show`, `rm`, `cp`, `stop` and `create` all working the same way.
A decision model takes a state, a message, an email, a ticket, any JSON, plus typed questions, and returns calibrated probabilities in a single forward pass rather than generating text, so answers come back in milliseconds.
Because it speaks TypeSafe's `/v1/systemone` wire format, any existing Jev client can point at a local Ollaya daemon instead of the hosted API by changing one environment variable, with an NVIDIA/CUDA or CPU-only path depending on the platform.
What you get
- Full Rust source code under the Apache 2.0 license
- The ollaya CLI and daemon, plus its model catalog on Hugging Face
Jev
Rust
TypeScript
Node.js
Claude Code
Codex
CodeRabbit Top10
Python
