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

# Kisuke

> AI conversations and project tools in Zen.

Use **Zen mode** to keep project tools beside your conversation. Connect **OpenAI, Anthropic, Google**, and other providers; choose **Claude Code**, **OpenAI Codex**, **Pi**, or another available harness.

<Frame caption="An implementation ready for review in Zen, beside the running Trail Notes preview. The conversation, project files, terminal, and browser remain in one workspace.">
  <img src="https://mintcdn.com/stormborneinc/kGoIXt2BW-FQgT25/images/screenshots/zen-verified-preview.jpg?fit=max&auto=format&n=kGoIXt2BW-FQgT25&q=85&s=47cb0180d302694407959d1b41242bf9" width="1686" height="971" alt="A completed implementation response in Zen beside the Trail Notes browser preview, with two checked trails and a Reset button. Files and Terminal are available in neighboring panel tabs." data-path="images/screenshots/zen-verified-preview.jpg" />
</Frame>

[Follow this workflow in Zen](/zen-mode#implement-and-verify-a-small-change), or explore the [provider integrations](/models/providers#choose-an-integration) and [agent harnesses](/models/overview#harnesses-in-kisuke).

Available models depend on provider access and harness support. A provider connection does not make every model available through every harness.

<Columns cols={2}>
  <Card title="Install and set up Kisuke" icon="download" href="/get-started/install">
    Choose the right desktop download, then sign in, set up Connect, and connect a provider.
  </Card>

  <Card title="Start with Zen mode" icon="wand-magic-sparkles" href="/zen-mode">
    Learn the workspace, bring tools beside your chat, and choose your default layout.
  </Card>

  <Card title="Choose your models" icon="sliders" href="/models/overview">
    Understand providers, harnesses, model selection, and reasoning controls.
  </Card>

  <Card title="Connect a provider" icon="plug" href="/models/providers">
    Set up OpenAI, Anthropic, Google, and other integrations offered in Settings.
  </Card>

  <Card title="Open your project" icon="folder-open" href="/projects/open-a-project">
    Choose a device and folder, then inspect the workspace before your first prompt.
  </Card>

  <Card title="Plan and review" icon="list-check" href="/conversations/planning">
    Ask for a plan, edit it, and decide when implementation should begin.
  </Card>
</Columns>

## Work through a change in Zen

New to the workspace? [Take a first tour](/zen-mode#take-a-first-tour) to ask about a project and inspect the answer with Files beside the conversation.

Ready to make a change? [Follow the implementation walkthrough](/zen-mode#implement-and-verify-a-small-change) from an agreed plan through tests, a working preview, and a scoped commit.

Keep the conversation and its supporting tools together:

1. [Attach a file or paste reference text](/conversations/attachments) and explain the outcome you want.
2. [Review permissions](/conversations/permissions) and [ask for a plan](/conversations/planning) before implementation.
3. [Read and edit files](/workspace/files), [run commands in Terminal](/workspace/terminal), and [preview a running app in Browser](/workspace/browser).
4. [Inspect Git changes and stage files](/workspace/git). Check the actual result before considering the work finished.

While an agent is working, [queue a next step or steer the current request](/conversations/follow-ups). The selected harness determines how a follow-up can be delivered.

## Return to earlier work

[Find a conversation](/conversations/find-conversations) by project, status, archive view, or device. [Rename and pin chats](/conversations/organize-and-archive) to make them easier to find, or search older archives in Settings.

An offline device or missing working folder can prevent a listed conversation from opening. The history guides explain how to distinguish those conditions from a hidden or archived row.

Away from your computer? [Pair your phone](/workspace/devices#pair-your-phone), keep Connect running on the project computer, and [find the existing chat on your phone](/conversations/find-conversations#find-and-resume-on-your-phone). Continue after checking its latest exchange and project context.

## Customize your setup

* **Project context:** [instruction files](/customization/project-instructions) describe repository conventions; [skills](/customization/skills) package reusable procedures; [custom commands](/customization/commands) save prompts with arguments.
* **Tools and integrations:** configure [MCP servers](/customization/mcp), inspect [plugins](/customization/plugins), or register a [plugin marketplace](/customization/plugin-marketplaces). Availability depends on the harness and runtime state.
* **Your own endpoint:** [add a custom model](/models/custom-models) when you have an OpenAI-compatible service and its model identifier.

Use [Settings and defaults](/reference/settings) to make Zen your launch layout and adjust the composer. The [keyboard reference](/reference/keyboard-shortcuts) covers common workspace actions, and the [glossary](/reference/glossary) explains how models, harnesses, conversations, goals, and tasks fit together.

If your first prompt cannot start, follow [Troubleshoot a first message](/help/starting-a-chat). A visible model selection alone does not confirm that the runtime has accepted it.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.