> ## Documentation Index
> Fetch the complete documentation index at: https://nmem.guoxudong.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Save an AI conversation

> Keep a genuinely valuable AI conversation.

<div className="course-meta" aria-label="Lesson information">
  <span><Icon icon="book-open" /> Essentials · Lesson 4 / 6</span>
  <span><Icon icon="clock-3" /> \~4 min</span>
  <span><Icon icon="user-round" /> Beginner</span>
</div>

AI conversations carry context that a one-line summary drops: what you asked, how the tool reasoned, and the back-and-forth that led to the answer. Mem's Threads keep the whole session so you can find it again later.

## What you'll accomplish

<Check>
  You'll save a genuinely valuable AI conversation into Mem and find it again by searching.
</Check>

## Watch how it's done

### Manual or automatic import

<iframe src="https://www.youtube.com/embed/8v3RnOE7dn8?autoplay=0" title="Demo: import an AI conversation from a coding tool" allowfullscreen="true" />

### Browser extension import

<iframe src="https://www.youtube.com/embed/ICFG0TkTmFY?autoplay=0" title="Demo: capture a web conversation with the browser extension" allowfullscreen="true" />

## Your turn

<Steps>
  <Step title="Pick a genuinely valuable AI conversation">
    Choose a real session where you solved a problem, made a decision, or produced something you'll want again. Skip trivial back-and-forth — pick something worth finding later.
  </Step>

  <Step title="Save it into Mem">
    Open **Threads → Import → Find AI conversations**. Mem scans this machine's coding-agent conversations and imports them.

    <Tip>
      Using a web AI chat? Install the Nowledge Mem Exchange browser extension to capture the current session. You can also import a single conversation from a Markdown file in **Threads → Import**.
    </Tip>
  </Step>

  <Step title="Confirm it's in Mem">
    Open **Threads** from the sidebar (or press **Cmd + 3** on macOS) and check that the conversation is there.
  </Step>

  <Step title="Search it back">
    In Threads, search for a detail only that conversation contains. It comes back.
  </Step>
</Steps>

## What you should see

<Check>
  The conversation you saved appears in Threads, and searching a detail from it finds it.
</Check>

<Note>
  Can't find it? Make sure the conversation finished importing, then search again using a word from its title or content.
</Note>

## Why this matters

A thread keeps the full process: what you asked, what the tool answered, and how the work evolved. A summary loses most of that. When something in the conversation is worth keeping long-term, you can distill it into memories that join your knowledge graph and show up in future searches.

## Go deeper

Want to understand how Threads work and how to distill them into memories? Read the [threads](https://mem.nowledge.co/docs/threads) page in the Nowledge Mem Docs.

## Next lesson

Next you'll learn: let Codex, Claude Code, Cursor, or other tools access Mem.

<Card title="Connect your AI →" horizontal href="/essentials/connect-your-ai" />