Opidocs
FeaturesAssistant

Memory

How your assistant remembers past conversations and uses that context to give you better answers over time.

Your assistant doesn't forget. Unlike a typical chatbot that starts fresh every time, your Opisense assistant carries forward what it's learned from your conversations. This means less repeating yourself and more relevant, personalized responses.

What memory means

Memory is the assistant's ability to recall information from your past interactions. When you tell it something important — your preferences, a decision you've made, context about a project — it stores that and uses it in future conversations.

This isn't just chat history. The assistant actively extracts and retains key details so it can reference them later, even across completely different conversation threads.

Session memory vs. long-term memory

There are two layers of memory:

  • Session memory is the conversation you're having right now. The assistant remembers everything in the current thread — every message, every follow-up, every file you've shared. This resets when you start a new conversation.

  • Long-term memory persists across sessions. The assistant extracts important details — your preferences, recurring topics, key decisions — and stores them so they carry forward into future conversations. This is what makes the assistant feel like it truly knows you.

Long-term memory builds gradually. The more you chat, the better your assistant understands your working style and preferences. It's worth having a few conversations to let it learn.

What it retains vs. what it forgets

The assistant is selective about what it stores in long-term memory. It prioritizes:

  • Preferences — How you like things formatted, your communication style, your go-to tools
  • Key decisions — Choices you've made that might come up again
  • Recurring context — Projects you mention often, people you work with, topics you care about
  • Explicit instructions — Things you've directly told it to remember

Casual, one-off exchanges (like small talk or throwaway questions) generally don't get stored long-term. The assistant focuses on what's useful.

Managing your memory

You're always in control. You can view and manage what the assistant remembers:

  • View memory — Check what the assistant has stored about you in the memory section of your assistant settings
  • Clear memory — Reset long-term memory if you want a fresh start. This won't affect your conversation history — just the extracted context the assistant carries forward.

Clearing memory is useful if your role has changed, you've switched projects, or you just want the assistant to start learning about you from scratch.

Privacy

Your memory is entirely private. No one else on your team can see what your assistant remembers about you. Each person has their own separate memory space. For more details, see Security and Privacy.

For a deeper understanding of how memory and knowledge work together, check out Knowledge and Memory.

On this page