content

AgenticGoKit Documentation

The Go Framework for Building Multi-Agent AI Systems

Go Version Go Version License License Go Report Card Go Report Card GitHub Stars GitHub Stars

Build intelligent agent workflows with dynamic tool integration, multi-provider LLM support, and enterprise-grade orchestration patterns. Go-native performance meets AI agent systems.

⚡ 5-Minute Demo

Create a collaborative multi-agent system with one command:

# Install the CLI
go install github.com/kunalkushwaha/agenticgokit/cmd/agentcli@latest

# Create a multi-agent research team
agentcli create research-team --orchestration-mode collaborative --agents 3 --visualize

cd research-team

# Set your API key
export AZURE_OPENAI_API_KEY=your-key-here
export AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
export AZURE_OPENAI_DEPLOYMENT=your-deployment-name

# Run the collaborative system
go run . -m "Research the latest developments in AI agent frameworks"

What you get:

  • ✅ Complete Go project with main.go, agentflow.toml, and go.mod
  • ✅ Three specialized agents working in parallel
  • ✅ Automatic result synthesis and error handling
  • ✅ Mermaid workflow diagrams generated
  • ✅ Production-ready project structure

🚀 Why AgenticGoKit?

🏃‍♂️ For Developers

  • Go-Native Performance: Compiled binaries, efficient memory usage
  • Type Safety: Compile-time error checking prevents runtime issues
  • Simple Deployment: Single binary, no complex Python environments
  • Native Concurrency: Goroutines for true parallel agent execution

🤖 For AI Systems

  • Multi-Agent Focus: Built specifically for agent orchestration
  • Memory & RAG: Built-in vector databases and knowledge management
  • Tool Integration: MCP protocol for dynamic tool discovery
  • Production Ready: Error handling, monitoring, scaling patterns

🎯 Quick Start Paths

🏃‍♂️ 5-Minute Start

Get your first agent running immediately

go get github.com/kunalkushwaha/agenticgokit

→ Start Building

🎓 Learn Step-by-Step

Follow guided tutorials to master concepts

→ Start Learning

🚀 Explore Examples

Run working examples and demos

git clone https://github.com/kunalkushwaha/agenticgokit
cd examples/04-rag-knowledge-base
docker-compose up -d
go run main.go

→ Browse Examples

🏗️ What You Can Build

🔍 Research Assistants

Multi-agent research teams with web search, analysis, and synthesis

agentcli create research-team \
  --orchestration-mode collaborative \
  --agents 3 --mcp-enabled --visualize

📊 Data Processing Pipelines

Sequential workflows with error handling and monitoring

agentcli create data-pipeline \
  --orchestration-mode sequential \
  --agents 4 --visualize

💬 Conversational Systems

Chat agents with persistent memory and context

agentcli create chat-system \
  --agents 2 --visualize

📚 Knowledge Bases

RAG-powered Q&A with document ingestion and vector search

agentcli create knowledge-base \
  --orchestration-mode collaborative \
  --agents 3 --visualize

📚 Documentation Structure

🚀 Learning Paths

New to AgenticGoKit? Follow these guided paths:

Beginner Path (30 minutes)

  1. 5-Minute Quickstart - Get running immediately
  2. Your First Agent - Build a simple agent
  3. Multi-Agent Collaboration - Agents working together

Intermediate Path (1 hour)

  1. Memory & RAG - Add knowledge capabilities
  2. Tool Integration - Connect external tools
  3. Core Concepts - Deep dive into fundamentals

Advanced Path (2+ hours)

  1. Advanced Patterns - Complex orchestration patterns
  2. Production Deployment - Deploy to production
  3. Performance Optimization - Scale your systems

📖 Documentation Sections

📚 Tutorials

Learning-oriented guides to help you understand AgenticGoKit:

🛠️ How-To Guides

Task-oriented guides for specific scenarios:

📋 Reference

Information-oriented documentation:

👥 Contributors

For developers contributing to AgenticGoKit:

🧠 Core Concepts

Multi-Agent Orchestration

// Collaborative agents (parallel execution)
agents := map[string]core.AgentHandler{
    "researcher": NewResearchAgent(),
    "analyzer":   NewAnalysisAgent(),
    "validator":  NewValidationAgent(),
}

runner := core.CreateCollaborativeRunner(agents, 30*time.Second)
result, err := runner.ProcessEvent(ctx, event)

Configuration-Based Setup

# agentflow.toml
[orchestration]
mode = "collaborative"
timeout_seconds = 30

[agent_memory]
provider = "pgvector"
enable_rag = true
chunk_size = 1000

[mcp]
enabled = true

Memory & RAG Integration

// Configure persistent memory with vector search
memory, err := core.NewMemory(core.AgentMemoryConfig{
    Provider: "pgvector",
    EnableRAG: true,
    EnableKnowledgeBase: true,
    ChunkSize: 1000,
})

Tool Integration (MCP)

// MCP tools are automatically discovered and integrated
// Agents can use web search, file operations, and custom tools
agent := agents.NewToolEnabledAgent("assistant", llmProvider, toolManager)

🌟 Current Features

  • 🤖 Multi-Agent Orchestration: Collaborative, sequential, loop, and mixed patterns
  • 🧠 Memory & RAG: PostgreSQL pgvector, Weaviate, and in-memory providers
  • 🔧 Tool Integration: MCP protocol support for dynamic tool discovery
  • ⚙️ Configuration Management: TOML-based configuration with environment overrides
  • 📊 Workflow Visualization: Automatic Mermaid diagram generation
  • 🎯 CLI Scaffolding: Generate complete projects with one command
  • 📈 Production Patterns: Error handling, retry logic, and monitoring hooks

🚀 Installation & Setup

# Install the CLI
go install github.com/kunalkushwaha/agenticgokit/cmd/agentcli@latest

# Create your first project
agentcli create my-agents --orchestration-mode collaborative --agents 3 --visualize

cd my-agents

Option 2: Go Module

go mod init my-agent-project
go get github.com/kunalkushwaha/agenticgokit

# Create agentflow.toml configuration file
# See reference/api/configuration.md for details

Environment Setup

# For Azure OpenAI (recommended)
export AZURE_OPENAI_API_KEY=your-key-here
export AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
export AZURE_OPENAI_DEPLOYMENT=your-deployment-name

# For OpenAI
export OPENAI_API_KEY=your-key-here

# For Ollama (local)
export OLLAMA_HOST=http://localhost:11434

🌍 Community & Support

💬 Get Help

🤝 Contribute

📢 Stay Updated

🏆 Why Choose AgenticGoKit?

🚀 Performance

  • Compiled Go: Native performance, efficient memory usage
  • Concurrent Processing: True parallel agent execution with goroutines
  • Single Binary: No complex runtime dependencies
  • Fast Startup: Instant initialization, no warm-up time

🛠️ Developer Experience

  • Type Safety: Compile-time error checking
  • CLI Scaffolding: Generate complete projects instantly
  • Configuration-Driven: Change behavior without code changes
  • Workflow Visualization: Automatic Mermaid diagrams

🤖 AI-First Design

  • Multi-Agent Focus: Built specifically for agent orchestration
  • Memory Integration: Built-in vector databases and RAG
  • Tool Ecosystem: MCP protocol for dynamic capabilities
  • Production Patterns: Error handling, retry logic, monitoring

🏭 Production Ready

  • Error Handling: Comprehensive error routing and recovery
  • Monitoring: Built-in logging and tracing capabilities
  • Scalability: Designed for horizontal scaling patterns
  • Configuration: Environment-based configuration management

🚀 Ready to Build?

🏃‍♂️ Start with 5-Minute Quickstart

Build your first multi-agent system in 5 minutes

🎓 Follow the Learning Path

Master AgenticGoKit with step-by-step tutorials

🚀 Explore Live Examples

See working multi-agent systems in action

⭐ Star us on GitHub • 📖 Read the Docs • 💬 Join Discussions

License

Apache 2.0 - see LICENSE for details.

AgenticGoKit: Where Go performance meets AI agent intelligence.