Open-source AI coworker, with memory https://www.rowboatlabs.com
Find a file
2025-04-07 17:19:58 +05:30
.github/workflows update next build action 2025-02-05 10:43:54 +05:30
apps Conditionally render testing feature based on use testing flag 2025-04-07 17:19:58 +05:30
assets Readme updates (#58) 2025-04-03 23:35:15 +05:30
.env.example Run mongodb in docker 2025-04-07 13:30:27 +05:30
.gitattributes Mega UI revamp 2025-04-03 17:56:31 +05:30
.gitignore Run mongodb in docker 2025-04-07 13:30:27 +05:30
docker-compose.yml Run mongodb in docker 2025-04-07 13:30:27 +05:30
LICENSE Fill license placeholder 2025-01-31 16:29:39 +05:30
README.md Update README.md 2025-04-07 16:49:47 +05:30

ui

Let AI build multi-agent workflows for you in minutes

Quickstart | Docs | Website | Discord

  • 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
    • 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!

Quick start

  1. Set your OpenAI key

    export OPENAI_API_KEY=your-openai-api-key
    
  2. Clone the repository and start Rowboat docker

    git clone git@github.com:rowboatlabs/rowboat.git
    cd rowboat
    docker-compose up --build
    
  3. Access the app at http://localhost:3000.

Demo

ui

Integrate with the Rowboat HTTP API

You can use the API directly at http://localhost:3000/api/v1/

  • Project ID is available in the URL of the project page
  • API Key can be generated from the project config page at /projects/<PROJECT_ID>/config
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"
        }
    ]
}'

which gives:

{
    "messages": [
        {
            "role": "assistant",
            "tool_calls": [
                {
                    "function": {
                        "arguments": "{\"location\":\"London\",\"units\":\"metric\"}",
                        "name": "weather_lookup_tool"
                    },
                    "id": "call_r6XKuVxmGRogofkyFZIacdL0",
                    "type": "function"
                }
            ],
            "agenticSender": "Example Agent",
            "agenticResponseType": "internal"
        }
    ],
    "state": {
        // .. state data
    }
}

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