Skip to main content
A Bindu agent powered by MiniMax’s M2.7 model via OpenAI-compatible API.

​
Code

Create minimax_example.py with the code below, or save it directly from your editor. 
"""MiniMax AI Research Agent

A Bindu agent powered by MiniMax's M2.7 model via OpenAI-compatible API.
MiniMax offers high-performance models with up to 1M context window.

Features:
- MiniMax M2.7 model (1M context)
- Web search integration via DuckDuckGo
- Research and summarization capabilities

Usage:
    python minimax_example.py

Environment:
    Requires MINIMAX_API_KEY in .env file
    Get your API key at https://platform.minimaxi.com
"""

import os
from bindu.penguin.bindufy import bindufy
from agno.agent import Agent
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.models.openai import OpenAILike

from dotenv import load_dotenv

load_dotenv()

# MiniMax API configuration
MINIMAX_API_KEY = os.getenv("MINIMAX_API_KEY")
MINIMAX_BASE_URL = "https://api.minimax.io/v1"

# Define your agent with MiniMax M2.7
agent = Agent(
    instructions="You are a research assistant that finds and summarizes information.",
    model=OpenAILike(
        id="MiniMax-M2.7",
        api_key=MINIMAX_API_KEY,
        base_url=MINIMAX_BASE_URL,
    ),
    tools=[DuckDuckGoTools()],
)


# Configuration
config = {
    "author": "your.email@example.com",
    "name": "minimax_research_agent",
    "description": "A research assistant agent powered by MiniMax AI",
    "deployment": {
        "url": os.getenv("BINDU_DEPLOYMENT_URL", "http://localhost:3773"),
        "expose": True,
        "cors_origins": ["http://localhost:5173"]
    },
}


# Handler function
def handler(messages: list[dict[str, str]]):
    """Process messages and return agent response.

    Args:
        messages: List of message dictionaries containing conversation history

    Returns:
        Agent response result
    """
    result = agent.run(input=messages)
    return result


# Bindu-fy it
if __name__ == "__main__":
    bindufy(config, handler)

​
How It Works

MiniMax Integration
  • Uses MiniMax M2.7 model with 1M context window
  • OpenAI-compatible API via OpenAILike model wrapper
  • High-performance research and analysis capabilities
Web Search
  • DuckDuckGoTools(): Enables web search for current information
  • Research assistant can find and summarize information from the web
  • Combines web search with MiniMax’s powerful reasoning
Configuration
  • Environment variable for deployment URL flexibility
  • Standard Bindu deployment on localhost:3773
  • CORS enabled for frontend integration

​
Dependencies

uv init
uv add bindu agno python-dotenv

​
Environment Setup

Create .env file: 
MINIMAX_API_KEY=your_minimax_api_key_here
BINDU_DEPLOYMENT_URL=http://localhost:3773
Get your MiniMax API key at https://platform.minimaxi.com

​
Run

uv run minimax_example.py
Examples:
  • “Research the latest developments in quantum computing”
  • “Find information about climate change and its effects”
  • “Summarize current trends in artificial intelligence”

​
Example API Calls

{
  "jsonrpc": "2.0",
  "method": "message/send",
  "params": {
    "message": {
      "role": "user",
      "kind": "message",
      "messageId": "9f11c870-5616-49ad-b187-d93cbb100001",
      "contextId": "9f11c870-5616-49ad-b187-d93cbb100002",
      "taskId": "9f11c870-5616-49ad-b187-d93cbb100003",
      "parts": [
        {
          "kind": "text",
          "text": "Research the latest developments in quantum computing"
        }
      ]
    },
    "configuration": {
      "acceptedOutputModes": ["application/json"]
    }
  },
  "id": "9f11c870-5616-49ad-b187-d93cbb100003"
}

{
  "jsonrpc": "2.0",
  "method": "tasks/get",
  "params": {
    "taskId": "9f11c870-5616-49ad-b187-d93cbb100003"
  },
  "id": "9f11c870-5616-49ad-b187-d93cbb100004"
}

​
Frontend Setup

# Clone the Bindu repository
git clone https://github.com/GetBindu/Bindu

# Navigate to frontend directory
cd frontend

# Install dependencies
npm install

# Start frontend development server
npm run dev
Open http://localhost:5173 and try to chat with the MiniMax research agent