Skip to content

Quick Start

Blades is a multimodal AI Agent framework based on Go, supporting custom models, tools, memory, middleware, etc., suitable for multi-turn conversations, chain-of-thought reasoning, and structured output scenarios.

Environment Setup

Ensure you have Go 1.20+ installed, then initialize your project and import Blades with the following commands:

cd your-project-name
go mod init your-project-name
go get github.com/go-kratos/blades

Create an Agent

Here is a complete example of building a simple chat Agent using the OpenAI model:

package main

import (
    "context"
    "log"

    "github.com/go-kratos/blades"
    "github.com/go-kratos/blades/contrib/openai"
    "github.com/openai/openai-go/v2/option"
)

func main() {
    // set up the OpenAI provider
    provider := openai.NewChatProvider(
        openai.WithChatOptions(
            option.WithAPIKey("YOUR_API_KEY"),
            option.WithBaseURL("YOUR_BASE_URL"),
        ),
    )
    // create agent
    agent, err := blades.NewAgent(
        "Blades Agent",
        blades.WithModel("YOUR_MODEL"), // or gpt-5, qwen3-max, etc.
        blades.WithProvider(provider),
        blades.WithInstructions("You are a helpful assistant that provides detailed and accurate information."),
    )
    if err != nil {
        log.Fatal(err)
    }
    // Create a new input message
    input := blades.UserMessage("What is the capital of France?") // Create a new input message
    // Run the agent
    runner := blades.NewRunner(agent)
    result, err := runner.Run(context.Background(), input)
    if err != nil {
        log.Fatal(err)
    }
    log.Println(result.Text())
}

Note

If you want to use another provider’s API, you need to set environment variables, for example:

export OPENAI_BASE_URL=https://api.deepseek.com

You need to set the environment variable OPENAI_API_KEY, for example:

export OPENAI_API_KEY=your-api-key

Supported Models and Providers

Provider	Model	Compatibility
OpenAI	ChatGPT, gpt-5, gpt-4, etc…	qwen3-mqx、deepseek-chat
Claude	Claude 3.7 Sonnet	-
Gemini	Gemini 2.5 Pro	-

Core Concepts Overview

Component	Description
Agent	Agent interface for integrating and coordinating models, tools, memory, and other functional agents
Tool	External capability plugins (e.g., calling APIs, querying databases)
Memory	Conversation memory management, supporting multi-turn context
Middleware	Middleware mechanism for cross-cutting concerns like logging, rate limiting, authentication
ModelProvider	Model adapter (e.g., OpenAI, DeepSeek), providing a unified calling interface

More Examples