ChatBotKit Node SDK
    Preparing search index...

    Module @chatbotkit/cli

    Follow on Twitter ChatBotKit CBK.AI NPM Email Discord

    ChatBotKit CLI

    A powerful command-line interface for ChatBotKit that provides both API management commands and an autonomous AI agent mode for interactive development tasks.

    Build lighter, future-proof AI agents. When you build with ChatBotKit, the heavy lifting happens on our servers—not in your application. This architectural advantage delivers:

    • 🪶 Lightweight Agents: Your agents stay lean because complex AI processing, model orchestration, and tool execution happen server-side. Less code in your app means faster load times and simpler maintenance.

    • 🛡️ Robust & Streamlined: Server-side processing provides a more reliable experience with built-in error handling, automatic retries, and consistent behavior across all platforms.

    • 🔄 Backward & Forward Compatible: As AI technology evolves—new models, new capabilities, new paradigms—your agents automatically benefit. No code changes required on your end.

    • 🔮 Future-Proof: Agents you build today will remain capable tomorrow. When we add support for new AI models or capabilities, your existing agents gain those powers without any updates to your codebase.

    This means you can focus on building great user experiences while ChatBotKit handles the complexity of the ever-changing AI landscape.

    Install globally via npm:

    npm install --global @chatbotkit/cli
    

    Set your ChatBotKit API token as an environment variable:

    export CHATBOTKIT_API_TOKEN=<your token here>
    

    The CLI automatically loads environment variables from the following locations (in order of precedence):

    1. .env.local - Project-specific local configuration (current directory)
    2. .env - Project configuration (current directory)
    3. ~/.cbk/env - Global user configuration (home directory fallback)

    This allows you to store your API token globally in ~/.cbk/env for convenience, while still being able to override it per-project using local .env files.

    Example ~/.cbk/env file:

    CHATBOTKIT_API_TOKEN=your_token_here
    

    Manage ChatBotKit resources directly from the command line:

    cbk api conversation list
    cbk api bot list

    Use cbk --help to see all available commands.

    Run an autonomous AI agent that can execute tasks with local file system and command access, while leveraging the full power of the ChatBotKit platform.

    cbk agent -p "Create a new file and write hello world to it"
    

    Local Tools:

    • read - Read file contents
    • write - Write content to a file
    • edit - Replace exact string occurrences (single match only)
    • find - Search for files using glob patterns
    • exec - Execute shell commands

    Platform Integration:

    The agent runs with complete ChatBotKit platform capabilities, including:

    • Access to all configured integrations and 3rd-party services
    • Authenticated sessions with external APIs
    • Dataset connections and skillsets
    • Custom abilities and functions

    This means your agent can interact with your local development environment while seamlessly accessing any ChatBotKit resources you've configured.

    Agent Options:

    • -p, --prompt <text> - Task to execute
    • -t, --tools <names> - Comma-separated list of tools to enable (defaults to all standard tools)
    • -m, --model <name> - AI model to use

    Example:

    # Run agent with specific tools only
    cbk agent -t read,write -p "Read package.json and create a backup"

    # Use custom timeout for long-running commands
    cbk agent -p "Run tests with 60 second timeout" -m gpt-5

    For comprehensive information about the ChatBotKit CLI SDK, including detailed documentation on its functionalities, helper methods, and configuration options, please visit our type documentation page.

    If you find a bug or would like to contribute to the ChatBotKit SDK, please open an issue or submit a pull request on the official GitHub repository.

    Modules

    color
    command/api
    env
    index
    input
    loader/hooks
    solution
    tools