Notes from the runtime — local LLM inference, native bindings, and embedded model deployment.https://mullama.cognisoc.com/en-ushttps://mullama.cognisoc.com/blog/why-six-bindings/https://mullama.cognisoc.com/blog/why-six-bindings/Most local LLM runtimes give you exactly one of two things: a hand-rolled binding in the maintainer's favorite language, or an HTTP daemon. Mullama refuses the choice. Here's why.Tue, 12 May 2026 00:00:00 GMThttps://mullama.cognisoc.com/blog/drop-in-for-ollama/https://mullama.cognisoc.com/blog/drop-in-for-ollama/Mullama is wire-compatible with Ollama at the CLI, the Modelfile format, the model registry, and the HTTP port. Existing client code keeps working. Here's exactly what stays the same and what's new.Wed, 22 Apr 2026 00:00:00 GMThttps://mullama.cognisoc.com/blog/embed-the-runtime/https://mullama.cognisoc.com/blog/embed-the-runtime/Daemons are great until you're shipping a desktop app, a CLI tool, or an on-device deployment. Mullama links into your binary as a static library. Here's what that unlocks — and what it costs.Sun, 15 Mar 2026 00:00:00 GMT