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

# Quickstart

> Install and run KiwiFS in 60 seconds.

## 1. Install

<Tabs>
  <Tab title="Shell">
    ```bash theme={null}
    curl -fsSL https://raw.githubusercontent.com/kiwifs/kiwifs/main/install.sh | sh
    ```
  </Tab>

  <Tab title="Go">
    ```bash theme={null}
    go install github.com/kiwifs/kiwifs@latest
    ```
  </Tab>

  <Tab title="Docker">
    ```bash theme={null}
    docker run -p 3333:3333 -v ./knowledge:/data ameliaanhlam/kiwifs
    ```

    <Note>
      The Docker image runs `kiwifs serve` with default settings. Skip to step 4 — init and serve are handled automatically.
    </Note>
  </Tab>
</Tabs>

## 2. Initialize a knowledge base

```bash theme={null}
kiwifs init --template knowledge --root ./knowledge
```

This creates a directory with starter files, a schema, and an agent playbook.

<Tip>
  Templates available: `knowledge` (default), `wiki`, `runbook`, `research`, `tasks`, `blank`. See [Init templates](/guides/templates) for details on each.
</Tip>

## 3. Start the server

```bash theme={null}
kiwifs serve --root ./knowledge
```

KiwiFS is now running at `http://localhost:3333`. Open it in your browser to see the web UI.

## 4. Write from your agent

<CodeGroup>
  ```bash Via REST theme={null}
  curl -X PUT 'http://localhost:3333/api/kiwi/file?path=concepts/auth.md' \
    -H "X-Actor: my-agent" \
    -d "# Authentication

  OAuth2 + JWT based authentication system."
  ```

  ```bash Via filesystem theme={null}
  echo "# Authentication" > ./knowledge/concepts/auth.md
  ```

  ```bash Via MCP theme={null}
  kiwifs mcp --root ./knowledge
  ```
</CodeGroup>

## 5. Search

```bash theme={null}
curl 'http://localhost:3333/api/kiwi/search?q=authentication'
```

## Connect an AI agent

Add KiwiFS as an MCP server in Claude Desktop or Cursor:

```json theme={null}
{
  "mcpServers": {
    "kiwifs": {
      "command": "kiwifs",
      "args": ["mcp", "--root", "/path/to/knowledge"]
    }
  }
}
```

Your agent now has access to **60+ MCP tools** for reading, writing, searching, querying, drafts, and more. See [MCP](/concepts/mcp) for the full tool reference.

## Next steps

<CardGroup cols={2}>
  <Card title="Configuration" icon="gear" href="/configuration">
    Auth, search, versioning, vector embeddings, and more.
  </Card>

  <Card title="Agent Interface" icon="robot" href="/concepts/agent-interface">
    Filesystem, REST, and MCP access patterns.
  </Card>

  <Card title="DQL" icon="database" href="/concepts/dql">
    Query frontmatter metadata with a SQL-like language.
  </Card>

  <Card title="Deploy with Docker" icon="docker" href="/deploy/docker">
    Production deployment with Docker Compose.
  </Card>

  <Card title="Web UI" icon="window" href="/guides/web-ui">
    Tree, editor, graph, Bases, and search.
  </Card>

  <Card title="Episodic memory" icon="brain" href="/concepts/episodic-memory">
    Episodes, consolidation, and memory reports.
  </Card>
</CardGroup>