
Ollama
CLI to run open LLMs locally for self-hosting and developer integration.

CLI to run open LLMs locally for self-hosting and developer integration.
Ollama is the easy on-ramp for local open models — `ollama run` and LAN APIs for other apps.
Offline laptop tweaks on small models; serious size still means cloud APIs.
Often paired with OpenRouter: prototype locally, promote prompts to hosted models.