Ollaya
Run open decision models locally behind a TypeSafe-compatible API, pulled and served the way Ollama runs LLMs
Ollaya is an open-source runtime for decision models, modelled on Ollama: one binary pulls models by name and serves them from a local daemon. It runs 16 model families, including Laya, Kev and Clef, and answers on TypeSafe's /v1/systemone endpoint, so existing Jev clients work after changing the base URL.
It ships a desktop app and command line for macOS, Windows and Linux, plus a Docker image. Every model runs on CPU; NVIDIA GPUs, and Apple silicon for Laya, cut a request to milliseconds. Apache-2.0, in beta, and not affiliated with Ollama or TypeSafe.
Pricing: Free
Choosing a local LLM runtime right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing a local LLM runtime right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Ollaya Alternatives
Explore 49 products in the Frameworks & Stacks category. View all Ollaya alternatives.
Magnitude
Open-source desktop inference engine that tunes its kernels to your hardware and connects local models to your agent.
GPT4All
Desktop app and Python SDK for running open-source LLMs locally on any device
Jan
Open-source desktop app for running LLMs locally with a clean GUI
Xinference
Open-source inference engine for 300+ open models, plus a hosted API and managed GPUs served from Australia
llamafile
Single-file executables that run LLMs locally on Linux, macOS, Windows and BSD with an OpenAI-compatible server
KoboldCpp
Single-binary llama.cpp runtime with an OpenAI-compatible API, web UI, image generation and speech
Work on Ollaya? Feature it at the top of Frameworks & Stacks.
Is your product missing?