Reply to thread

Message: <blockquote data-quote="Willis Rice" data-source="post: 28573" data-attributes="member: 10864">Hey everyone,I’ve been messing around with local LLMs using Ollama for a while, but I'm hitting the point where I need to take things to the next level and I'm looking for some advice from anyone who has experience here.I am building a custom AI backend for automated assistant bot Right now, I'm using Ollama to run the models, but I need the agent to have long-term persistent memory and a strict, consistent persona that doesn't break character.The Problem:Ollama is great for testing out of the box, but handling dynamic memory (saving past chats) and keeping the bot acting exactly how I want it to over long conversations is getting tricky. I'm moving toward building a custom programmatic architecture (using Python/TypeScript) to handle the prompt stitching and database memory outside of Ollama.What I’m looking for advice on:<ol> <li data-xf-list-type="ol">Has anyone successfully built a persistent memory system (like SQLite or vector databases) that feeds context into a local Ollama model?</li> <li data-xf-list-type="ol">For those running custom personas—are you just using really good dynamic system prompts, or did you actually bite the bullet and fine-tune (LoRA) your own base model?</li> <li data-xf-list-type="ol">Are there better alternatives you'd recommend over Ollama if my main goal is full API control and raw, unfiltered outputs?</li> </ol>Would love to hear from anyone who has built custom stacks around local models. Thanks!</blockquote>

Name

Verification