rowboat/README.md

RowboatX - CLI Tool for Background Agents

• ✨ Create background agents with full shell access
  • E.g. "Generate a NotebookLM-style podcast from my saved articles every morning"
• 🔧 Connect any MCP server to add capabilities
  • Add MCP servers and RowboatX handles the integration
• 🎯 Let RowboatX control and monitor your background agents
  • Easily inspect state on the filesystem

Inspired by Claude Code, RowboatX brings the same shell-native power to background automations.

Quick start

1. Set your LLM API key. Supports OpenAI, Anthropic, Gemini, OpenRouter, LiteLLM, Ollama, and more.

   export OPENAI_API_KEY=your-openai-api-key  
   

2. Install RowboatX

   npx @rowboatlabs/rowboatx
   

Demo

Examples

Add and Manage MCP servers

$ rowboatx

• Add MCP: 'Add this MCP server config: <config> '
• Explore tools: 'What tools are there in <server-name> '

Create background agents

$ rowboatx

• 'Create agent to do X.'
• '... Attach the correct tools from <mcp-server-name> to the agent'
• '... Allow the agent to run shell commands including ffmpeg'

Schedule and monitor agents

$ rowboatx

• 'Make agent <background-agent-name> run every day at 10 AM'
• 'What agents do I have scheduled to run and at what times'
• 'When was <background-agent-name> last run'
• 'Are any agents waiting for my input or confirmation'

Run background agents manually

rowboatx --agent=<agent-name> --input="xyz" --no-interactive=true

rowboatx --agent=<agent-name> --run_id=<run_id> # resume from a previous run

Models support

You can configure your models in ~/.rowboat/config/models.json

{
  "providers": {
    "openai": {
      "flavor": "openai"
    },
    "anthropic": {
      "flavor": "anthropic"
    },
    "google": {
      "flavor": "google"
    },
    "ollama": {
      "flavor": "ollama"
    }
  },
  "defaults": {
    "provider": "openai",
    "model": "gpt-5"
  }
}

Rowboat Classic UI

To use Rowboat Classic UI (not RowboatX), refer to Classic.