Show HN: I built Otis, a minimal AI agent that runs local models out of the box

petrenk0n 19 points 3 comments September 14, 2026
triangllabs.ai · View on Hacker News

Hi everyone, Been working on Otis, an open-source ai agent that gives you one minimal experience across local and hosted open-weight models, privacy-focused by design. On setup it recommends a local model based on the hardware Otis is running on, downloads it and runs it through llama.cpp for you. Ollama, LM Studio and Nvidia PAIR are supported too. Excited for everyone to try it and all feedback is welcome!

Discussion Highlights (2 comments)

sbankowi

I am looked at the website, but I am not able to understand what problem you are trying to solve. Or why would I use you? (How are you differentiating yourself?) I see you are reliant on ollama and llama.cpp (for example), so why should I not just use those directly if I am focused on local first models. (llama.cpp already makes recommendations on what models to run.) If the argument is then that you are more of an agentic experience, then how are you differentiating yourself from something like the Hermes Agent? I think more reasons on why this vs. what is already out there would be needed.

code_devil

I have also been building a local minimal AI agent too =P. It's still a TUI as I am still testing it out, though plan to make it into a native app too. Good luck to you too Peter.

Semantic search powered by Rivestack pgvector
6,607 stories · 60,417 chunks indexed