rowboat

• ✨ Start from an idea -> copilot builds your multi-agent workflows
  • E.g. "Build me an assistant for a food delivery company to handle delivery status and missing items. Include the necessary tools."
• 🌐 Connect MCP servers
  • Add the MCP servers in settings -> import the tools into Rowboat.
• 📞 Integrate into your app using the HTTP API or Python SDK
  • Grab the project ID and generated API key from settings and use the API.

Powered by OpenAI's Agents SDK, Rowboat is the fastest way to build multi-agents!

1. Set your OpenAI key

   export OPENAI_API_KEY=your-openai-api-key

2. Clone the repository and start Rowboat

   git clone git@github.com:rowboatlabs/rowboat.git
   cd rowboat
   ./start.sh

3. Access the app at http://localhost:3000.

Note: We have added native RAG support including file-uploads and URL scraping. See the RAG section of our docs for this.

Note: See the Using custom LLM providers section of our docs for using custom providers like OpenRouter and LiteLLM.

There are 2 ways to integrate with the agents you create in Rowboat

1. HTTP API

   • You can use the API directly at http://localhost:3000/api/v1/
   • See API Docs for details

   curl --location 'http://localhost:3000/api/v1/<PROJECT_ID>/chat' \
   --header 'Content-Type: application/json' \
   --header 'Authorization: Bearer <API_KEY>' \
   --data '{
       "messages": [
           {
               "role": "user",
               "content": "tell me the weather in london in metric units"
           }
       ],
       "state": null
   }'

2. Python SDK You can use the included Python SDK to interact with the Agents

   pip install rowboat
   

   See SDK Docs for details. Here is a quick example:

   from rowboat import Client, StatefulChat
   from rowboat.schema import UserMessage, SystemMessage
   
   # Initialize the client
   client = Client(
       host="http://localhost:3000",
       project_id="<PROJECT_ID>",
       api_key="<API_KEY>"
   )
   
   # Create a stateful chat session (recommended)
   chat = StatefulChat(client)
   response = chat.run("What's the weather in London?")
   print(response)
   
   # Or use the low-level client API
   messages = [
       SystemMessage(role='system', content="You are a helpful assistant"),
       UserMessage(role='user', content="Hello, how are you?")
   ]
   
   # Get response
   response = client.chat(messages=messages)
   print(response.messages[-1].content)

Refer to Docs to learn how to start building agents with Rowboat.