Ollama

I use Ollama (CLI and their npm as a dev) + HF because it just works.

> There are plenty of user friendly GUIs or wrappers for it That's why I use Ollama.

I find that agentic work and development is a mixture of agents and workflows outside of this project and I use all of them openai, anthropic , ollama etc..

And I’ve just been using the usually neutered ollama version.

I use Owen on my MacBook m1 (16gb) daily, running inside Ollama.

I use llama-swap to emulate the Ollama experience.

Highly recommend just dropping Ollama.

I’ve been using Ollama for months because it ‘just worked,’

I use Ollama in a non root podman instance.

Chat, say, through ollama works well.

I use Ollama and kinda just assumed that Ollama would have everything except for context length (which I've explicitly overwritten) setup properly for me.

We use Ollama's gemma4 model as the LLM, LangChain to communicate with the model, and Obsidian to view the generated markdown documents.