Ollama exposes local models over an OpenAI-compatible API. Compresh sits between your client and an Ollama-hosted model.
Under verification
This integration is documented as a planned path. We have not yet completed end-to-end verification on our own machine. Install steps will appear in this page once they are confirmed working. Until then, please open an issue if you want to try it and we'll fast-track verification.
Hook Not applicable
Not applicable.
MCP Not applicable
Not applicable.
Proxy SOON
Configuration is identical to the OpenAI SDK pattern. Verification pending.