Agno-GoHigh-Performance Multi-Agent Framework

Quick Example ​

Create an AI agent with tools in just a few lines:

package main

import (
    "context"
    "fmt"
    "github.com/rexleimo/agno-go/pkg/agno/agent"
    "github.com/rexleimo/agno-go/pkg/agno/models/openai"
    "github.com/rexleimo/agno-go/pkg/agno/tools/calculator"
)

func main() {
    // Create model
    model, _ := openai.New("gpt-4o-mini", openai.Config{
        APIKey: "your-api-key",
    })

    // Create agent with tools
    ag, _ := agent.New(agent.Config{
        Name:     "Math Assistant",
        Model:    model,
        Toolkits: []toolkit.Toolkit{calculator.New()},
    })

    // Run agent
    output, _ := ag.Run(context.Background(), "What is 25 * 4 + 15?")
    fmt.Println(output.Content) // Output: 115
}

Performance Comparison ​

Why Agno-Go? ​

Built for Production ​

Agno-Go isn't just a framework—it's a complete production system. The included AgentOS server provides:

• RESTful API with OpenAPI 3.0 specification
• Session management for multi-turn conversations
• Thread-safe agent registry
• Health monitoring and structured logging
• CORS support and request timeout handling

KISS Principle ​

Following the Keep It Simple, Stupid philosophy:

• 3 core LLM providers (not 45+) - OpenAI, Anthropic, Ollama
• Essential tools (not 115+) - Calculator, HTTP, File, Search
• Quality over quantity - Focus on production-ready features

Developer Experience ​

• Type-Safe: Go's strong typing catches errors at compile time
• Fast Builds: Go's compilation speed enables rapid iteration
• Easy Deployment: Single binary with no runtime dependencies
• Great Tooling: Built-in testing, profiling, and race detection

Get Started in 5 Minutes ​

# Clone repository
git clone https://github.com/rexleimo/agno-Go.git
cd agno-Go

# Set API key
export OPENAI_API_KEY=sk-your-key-here

# Run example
go run cmd/examples/simple_agent/main.go

# Or start AgentOS server
docker-compose up -d
curl http://localhost:8080/health

What's Included ​

• Core Framework: Agent, Team (4 modes), Workflow (5 primitives)
• Models: OpenAI, Anthropic Claude, Ollama, DeepSeek, Gemini, ModelScope
• Tools: Calculator (75.6%), HTTP (88.9%), File (76.2%), Search (92.1%)
• MCP Integration: Model Context Protocol support for connecting to any MCP server
• RAG: ChromaDB integration + OpenAI embeddings
• AgentOS: Production HTTP server (65.0% coverage)
• Examples: 7 working examples covering all features
• Docs: Complete guides, API reference, deployment instructions

Community ​

• GitHub: rexleimo/agno-Go
• Issues: Report bugs and request features
• Discussions: Ask questions and share ideas

License ​

Agno-Go is released under the MIT License.

Inspired by Agno (Python) framework.