Ollaya – Ollama for open-source, Jev-style decision models

	Ollaya – Ollama for open-source, Jev-style decision models(ollaya.dev)
	604 points by Ardakilic 18 days ago \| 145 comments
	tl;dr: Ollaya is an open-source, Ollama-style local runtime for "decision models" that return typed, calibrated answers (choice, score, yes/no) to questions about text or JSON in a single forward pass, rather than token-by-token generation. It's API-compatible with TypeSafe's Jev (drop-in with the official SDK), bundles open models like winnow, laya, kev, and decider, and runs on macOS, Windows, Linux, and Docker with NVIDIA GPU or CPU. Benchmarks claim winnow:e4b hits 0.722 accuracy at 89ms on an RTX 4090, close to Jev's hosted 0.738.
	HN Discussion: ~Concern about OSS rapidly copying startup innovations undermining Jev's business model ↑Defense of Jev's underlying innovation as non-trivial and worth building on ↓Skepticism that the bundled open models (Laya) match Jev's actual quality ↓Questioning the practical usefulness and how decision models differ from rerankers/classifiers ↓Criticism that Ollaya is derivative/infringing on Ollama's branding and could be obsoleted