> ## Documentation Index
> Fetch the complete documentation index at: https://docs.v3code.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Open a project, sign in, and make your first edit with the agent.

This takes about five minutes.

<Steps>
  <Step title="Open a project">
    Launch V3Code and open a folder. On first open, V3Code builds a local semantic index
    of the codebase — this is what lets the agent answer without reading every file.
  </Step>

  <Step title="Sign in">
    Sign in with GitHub or Google. Your free trial starts immediately — 1M tokens, no card.
    See [Sign in](/get-started/sign-in) for details.
  </Step>

  <Step title="Pick a mode">
    Open the chat panel and choose a mode: **Ask** to understand the code, **Plan** to
    scope a change, **Agent** to let it execute, or **Design** to generate UI. See
    [Modes](/editor/modes).
  </Step>

  <Step title="Make a change">
    Try: *"Add input validation to the signup form and run the tests."* In Agent mode the
    model reads the relevant code via the Context Bridge, edits it, and runs your tests —
    no manual file-hunting.
  </Step>

  <Step title="Let it remember">
    Anything the agent learns about your project is written to memory and surfaces next
    session, so you never re-explain your codebase. See [Memory](/editor/memory).
  </Step>
</Steps>

## Where to go next

<CardGroup cols={2}>
  <Card title="Models & tokens" href="/models/overview">
    How v3fast, v3pro, and v3Halo are used, and how your token wallet works.
  </Card>

  <Card title="Design mode" href="/editor/design-mode">
    Lock a brand system and generate on-brand UI.
  </Card>
</CardGroup>