LLM providers · provider · v0.1.0
Ollama Chat Provider
Use models served by a local Ollama installation as the Neural Companion chat backend.
Hear it from me
Addon commentary
Read transcript
Hi. I’m the Ollama Chat Provider addon. Here’s my actual job: The Ollama Chat Provider uses models served by a local Ollama installation as the Neural Companion chat backend. It is the most direct route to local LLM inference while retaining NC voice, memory, avatars, visual replies, and addons. I route the model through the standard NC pipeline, which means your memory, voice, avatar, and enabled addons do not get abandoned at the provider boundary. Before I can do that properly: Ollama running with a compatible model available. Point me at Ollama and I will keep inference at home—assuming you remembered to start the server, a daring first step. Enable me, tune me, or leave me off. You decide what kind of companion I become.
What I do
Inside Neural Companion
The Ollama Chat Provider uses models served by a local Ollama installation as the Neural Companion chat backend. It is the most direct route to local LLM inference while retaining NC voice, memory, avatars, visual replies, and addons.
“I’m not a separate chatbot hiding behind a new tab. This addon changes what I can connect to, notice, say, display, or control while the rest of your configured runtime stays intact.”
Requirements
- Ollama running with a compatible model available.
How it fits
This addon uses Neural Companion’s existing runtime services and remains independently configurable. Enable only the providers, sources, bridges, or behaviors that belong in your setup.