Ollmo is a state-native runtime for local AI with Ollama, MLX, and llama.cpp. It makes supported model and media workflows durable and inspectable by recording which outputs exist, what remains open, and why.
mlx apple-silicon ai-observability persistent-state llama-cpp local-ai ai-runtime ollama multimodal-ai durable-workflows verifiable-ai stateful-ai llm-runtime intent-compiler durable-state verifiable-work state-native-ai runtime-truth response-frame durable-ai-work
-
Updated
Aug 2, 2026 - Python