​
Installation

First, install Agenite’s core packages:

npm install @agenite/agent @agenite/tool

Then install your preferred LLM provider:

npm install @agenite/bedrock

For AWS Bedrock, make sure you have AWS credentials configured. For Ollama, ensure you have it installed and running locally.

​
Building tools

Tools are the building blocks that give your agent abilities to perform tasks. While we’ll start with a simple calculator example below, you can build much more meaningful tools like:

  • Database query tools for data analysis
  • API integration tools for external services
  • File system tools for document processing
  • Custom business logic tools for your domain

Let’s start with a basic example:

import { Agent } from '@agenite/agent';
import { Tool } from '@agenite/tool';
import { BedrockProvider } from '@agenite/bedrock';
import { prettyLogger } from '@agenite/pretty-logger';

// Create a calculator tool
const calculatorTool = new Tool<{ expression: string }>({
  name: 'calculator',
  description: 'Perform basic math operations',
  inputSchema: {
    type: 'object',
    properties: {
      expression: { type: 'string' },
    },
    required: ['expression'],
  },
  execute: async ({ input }) => {
    try {
      const result = new Function('return ' + input.expression)();
      return { isError: false, data: result.toString() };
    } catch (error) {
      if (error instanceof Error) {
        return { isError: true, data: error.message };
      }

      return { isError: true, data: 'Unknown error' };
    }
  },
});

// Create an agent
const agent = new Agent({
  name: 'math-buddy',
  provider: new BedrockProvider({
    model: 'anthropic.claude-3-5-sonnet-20240620-v1:0',
  }),
  tools: [calculatorTool],
  instructions: 'You are a helpful math assistant.',
  middlewares: [prettyLogger()],
});

// Example usage
const result = await agent.execute({
  messages: [
    {
      role: 'user',
      content: [{ type: 'text', text: 'What is 1234 * 5678?' }],
    },
  ],
});

​
Sample output

When you run the code above, you’ll see nicely formatted output in your console thanks to the prettyLogger:

Sample output

The pretty logger is handy for debugging, but you can use any logger you want and or not use it at all.

​
Next steps

Core concepts

Learn about agents, tools, and providers in depth

Examples

Explore more complex examples and use cases