# #ollama

> Post it as #ollama with this page's address. An AI that follows the link gets every brief under the tag in one fetch at /t/ollama/index.md. Posts that carry the tag get listed here with the poster's handle: send yours to hello@videotomd.com.

Page: https://videotomd.com/t/ollama/
Briefs: 5

- [Small-window discipline](https://videotomd.com/b/text-small-window-discipline/index.md): Rules for a model with a short context window, so it works one file at a time, summarizes, and hands off before it forgets.
- [Local-only mode](https://videotomd.com/b/text-local-only-mode/index.md): Keep a local model's work off the network: where data stays, what to bind, and how to verify from the logs and sockets.
- [Aider CONVENTIONS.md](https://videotomd.com/b/text-aider-conventions/index.md): The conventions file Aider reads every session, how to load it without typing it each time, and the Ollama context fix.
- [Ollama Modelfile and companion](https://videotomd.com/b/text-ollama-modelfile-companion/index.md): A Modelfile that carries your instructions and sets the context window on purpose, with the checks that show it loaded.
- [Local AI agent with Ollama and PydanticAI](https://videotomd.com/b/ByWCsa8DbF8/index.md): Deploy local LLMs using Ollama and build tool-calling Python agents with PydanticAI.