Private and local deployment with ClawAI

What running locally actually changes

A cloud provider elsewhere in ClawAI’s catalog runs a model on its own infrastructure and charges per request; Ollama and llama.cpp instead load an open-weight model onto hardware you control, so the request never leaves it. That changes who can see the request, not what any given model is capable of.

Local-Only and Privacy-First routing modes

Local-Only routing keeps every request on hardware you control, using Ollama or llama.cpp rather than any cloud provider. Privacy-First routing is a separate mode with its own priorities; both exist because not every workload should default to Auto routing, and choosing between them is a deliberate decision rather than a default to leave unexamined.

When a private or local workload is the right shape

A private or local workload is defined by where the request runs, not by what kind of task it is — coding, writing or research can all be run this way if the requirement is that nothing leaves hardware you control. See choosing a model for private, local workloads and what is local-first AI, both linked below, for the trade-offs to weigh.

Questions people ask

What is the difference between Local-Only and Privacy-First routing?

Local-Only keeps every request on hardware you control via Ollama or llama.cpp; Privacy-First is a separate routing mode with its own priorities. Both exist because not every workload should default to Auto routing.

Which open-weight model should I run locally?

This page does not recommend one — see what is local-first AI, linked below, for how to think about the choice, since the right model depends on your hardware and task.

Can I run any kind of task locally, or only certain ones?

A private or local workload is defined by where the request runs, not by the task — coding, writing, or research can all run this way if staying on hardware you control matters more than which task it is.