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

# Connect Life Note to your AI

> Bring your private journal into the AI you already use — Claude, ChatGPT, Claude Code, Cursor — as a read-only memory layer.

Your journal is where you think most honestly. Connect it to the AI you already use — in a chat app or in your terminal — so it can draw on your real reflections, wisdom, and goals. Read-only, private, and only when you ask.

## Two ways to connect

<CardGroup cols={2}>
  <Card title="In a chat app — no install" icon="comments">
    Add Life Note to **Claude** or **ChatGPT** and sign in once. Best for most people.
  </Card>

  <Card title="In your terminal or coding agent" icon="terminal">
    The `lifenote` command-line tool, for Claude Code, Cursor, and Codex. Best for developers.
  </Card>
</CardGroup>

## Connect in Claude or ChatGPT

No install needed — you just add a connector once.

<Steps>
  <Step title="In Claude (claude.ai)">
    Open **Settings → Connectors → Add custom connector**, paste the URL below, then **Connect** and sign in with your Life Note account.
  </Step>

  <Step title="In ChatGPT (Pro and above)">
    Open **Settings → Connectors** and add a custom connector with the same URL, then sign in.
  </Step>
</Steps>

Life Note connector URL:

```
https://mcp.mylifenote.ai/mcp
```

<Note>
  Adding a custom connector may require a paid Claude or ChatGPT plan. It also works with Gemini Enterprise and other MCP-compatible assistants.
</Note>

## What to ask — start here

Once connected, just talk normally. Not sure where to begin? Match it to how you're feeling:

<CardGroup cols={2}>
  <Card title="When you're feeling down" icon="cloud-rain">
    *"Look back through my journal and remind me of my small wins and the moments I actually grew — evidence I'm further along than I feel."*
  </Card>

  <Card title="When you're angry or hurt" icon="fire">
    *"I'm worked up about this. What have I written before about this person or situation — and what usually helps me settle?"*
  </Card>

  <Card title="When you want clarity" icon="lightbulb">
    *"Across my recent entries, what are my top recurring patterns — and the triggers behind them?"*
  </Card>

  <Card title="When you want to grow" icon="seedling">
    *"What blind spot keeps showing up in my writing — and what have my mentors said that speaks to it?"*
  </Card>

  <Card title="When you're facing a decision" icon="signs-post">
    *"I'm torn. Based on what I've written and my Life Goal, what do I actually value here?"*
  </Card>

  <Card title="When you feel adrift" icon="compass">
    *"What am I working on right now, and where am I drifting from this year's focus?"*
  </Card>
</CardGroup>

<Note>
  **Read-only and private.** Your AI can *read* your journal, wisdom, practices, and goals. It **cannot** write to your journal, change your settings, or access anyone else's data. Your sign-in token is stored securely — never in plain text — and you can disconnect any time from Settings.
</Note>

***

## For developers — the CLI

Prefer the terminal, or work in a coding agent? Install the `lifenote` CLI for the same journal, at the command line.

<Steps>
  <Step title="Install & sign in">
    Requires Python 3.10+. We recommend [pipx](https://pipx.pypa.io/):

    ```bash theme={null}
    pipx install lifenote
    lifenote auth login
    ```
  </Step>

  <Step title="Connect it to your coding agent">
    Claude Code — run this. Cursor and Codex use the same pattern; for Claude Desktop, add it to your MCP config.

    ```bash theme={null}
    claude mcp add lifenote -- lifenote mcp
    ```
  </Step>

  <Step title="Teach your agent when to use it">
    Install the bundled skill so your agent knows when to reach for your journal — and when not to:

    ```bash theme={null}
    lifenote skills install
    ```
  </Step>

  <Step title="Or use it straight from the terminal">
    Search your journal and pipe the results into any agent:

    ```bash theme={null}
    lifenote today
    lifenote search "anxiety about launch"
    lifenote search "burnout" --json | claude "summarize the patterns"
    ```
  </Step>
</Steps>

### What your agent can do

14 read-only tools span your journal, saved wisdom, mentor conversations, practices & quests, and life direction — so every scenario above works from the terminal too. Power-user asks:

> *"Cross-reference my journal and my saved wisdom on burnout — where do they agree, where do they diverge?"*
>
> *"Pull my last month of entries and draft a weekly-review summary I can paste into my journal."*
>
> *"Given my Life Goal and this year's focus, what have I actually made progress on — with evidence from my entries?"*

## Learn more

<CardGroup cols={2}>
  <Card title="GitHub — docs & source" icon="github" href="https://github.com/dandanbang/lifenote-cli">
    Setup for each agent, all commands, the full tool list, and the source code.
  </Card>

  <Card title="Install from PyPI" icon="python" href="https://pypi.org/project/lifenote/">
    The published `lifenote` package.
  </Card>
</CardGroup>