Back to Go Micro

Go Micro

README.md

5.26.08.5 KB
Original Source

Go Micro

Go Micro is a framework for building services and agents in Go.

Write services — they register, discover each other, and communicate via RPC and events. Every endpoint is automatically an AI-callable tool via MCP. Build agents to manage them intelligently. Both are Go code, both use the same primitives, both deploy the same way.

Sponsors

<a href="https://go-micro.dev/blog/3"></a>    <a href="https://go-micro.dev/blog/8"></a>

Quick Start

Install the CLI:

bash
# Binary (no Go required)
curl -fsSL https://go-micro.dev/install.sh | sh

# Or with Go
go install go-micro.dev/v5/cmd/[email protected]

Generate services from a description and start them:

bash
micro run --prompt "a task management system with categories" --provider anthropic

The AI designs the architecture, you review it, then it generates handlers with real business logic, compiles them, and starts them:

Services:
  ● task — Task management with status tracking
  ● project — Project organization

Generate? [Y/n]

Micro
  Services:
    ● task
    ● project
  Agents:
    ◆ agent

Then talk to your services from the console:

> Create a project called Launch, then add three tasks to it

→ project_Project_Create({"name":"Launch"})
← {"record":{"id":"p1..."},"success":true}
→ task_Task_Create({"title":"Design specs","project_id":"p1..."})
→ task_Task_Create({"title":"Write code","project_id":"p1..."})
→ task_Task_Create({"title":"Ship it","project_id":"p1..."})

Created Work category and added 'Finish report' task to it.

When you need a capability that doesn't exist, the agent generates a new service mid-conversation:

> I need to track shipping. Create a shipment for order 123 to London.

  ⚡ generating shipping service...
  ✓ shipping
  → shipping_Shipping_Create({"order_id":"123","destination":"London"})
  ← {"record":{"id":"xyz...","status":"pending"}}

  Created shipment for order 123 going to London.

Edit the generated code by hand at any time — re-running preserves your changes. Read more.

Writing Services

Under the hood, a service is a struct with methods. Doc comments and @example tags become tool descriptions for AI agents automatically.

go
package main

import (
    "go-micro.dev/v5"
)

type Request struct {
    Name string `json:"name"`
}

type Response struct {
    Message string `json:"message"`
}

type Say struct{}

// Hello greets a person by name.
// @example {"name": "Alice"}
func (h *Say) Hello(ctx context.Context, req *Request, rsp *Response) error {
    rsp.Message = "Hello " + req.Name
    return nil
}

func main() {
    service := micro.New("greeter")
    service.Handle(new(Say))
    service.Run()
}

Run it and everything is accessible — REST, gRPC, MCP, agent playground:

bash
micro run
# Dashboard:   http://localhost:8080
# API:         http://localhost:8080/api/{service}/{method}
# Agent:       http://localhost:8080/agent
# MCP Tools:   http://localhost:8080/mcp/tools

You can also scaffold a service from a template:

bash
micro new helloworld
micro new contacts --template crud

Building Agents

An Agent is a service with an LLM inside it. It has a proto-defined Agent.Chat RPC endpoint, registers in the registry, and is callable like any service:

go
agent := micro.NewAgent("task-mgr",
    micro.AgentServices("task", "project"),
    micro.AgentPrompt("You manage tasks and projects. You understand deadlines and priorities."),
    micro.AgentProvider("anthropic"),
)
agent.Run()

The agent discovers its services from the registry, scopes its tools to their endpoints, and maintains conversation memory in the store. It registers itself so micro chat and other agents can find it.

go
// Programmatic interaction
resp, _ := agent.Ask(ctx, "What tasks are overdue?")
fmt.Println(resp.Reply)

Multiple agents coordinate via RPC — each is a service with an Agent.Chat endpoint. micro chat routes to the right one.

bash
micro agent list                    # list registered agents
micro call task-mgr Agent.Chat '{"message": "What tasks are overdue?"}'

Features

CategoryWhatDetails
AIAgentsmicro.NewAgent() — intelligent layer that manages services
AIFlowsmicro.NewFlow() — event-driven LLM orchestration
AIMCP gatewayEvery endpoint is an AI tool automatically
AI7 LLM providersAnthropic, OpenAI, Gemini, Groq, Mistral, Together, Atlas Cloud
AIInteractive consolemicro run includes a chat console for talking to services
AIService generationmicro run --prompt — describe a system, get running services
DiscoveryService registrymDNS (default), Consul, etcd
CommunicationRPC client/servergRPC transport, load balancing, streaming
MessagingPub/sub eventsNATS, RabbitMQ, HTTP broker
StorageKey-value storeFile (bbolt), Postgres, NATS KV
DataTyped model layerCRUD + queries, SQLite/Postgres backends
DXHot reloadmicro run watches files, rebuilds on change
DXTemplatesmicro new --template crud/pubsub/api
DeployOne-command deploymicro deploy user@server — SSH + systemd, no Docker
PluginsEverything swappableAll abstractions are Go interfaces

CLI

CommandPurpose
micro run --prompt "..."Generate services + agent, start with interactive console
micro runDev mode: hot reload, gateway, interactive console
micro run -dDetached mode (no console)
micro chatStandalone chat (when not using micro run)
micro agent listList registered agents
micro new myserviceScaffold a service
micro call service endpoint '{}'Call a service or agent from the CLI
micro buildCompile production binaries
micro deploy user@serverDeploy via SSH + systemd

Multi-Service Projects

Run multiple services together:

go
users := micro.New("users", micro.Address(":9001"))
orders := micro.New("orders", micro.Address(":9002"))

users.Handle(new(Users))
orders.Handle(new(Orders))

g := micro.NewGroup(users, orders)
g.Run()

Or use a micro.mu config file:

service users
    path ./users

service orders
    path ./orders
    depends users

Data Model

Typed persistence with CRUD and queries:

go
type User struct {
    ID    string `json:"id" model:"key"`
    Name  string `json:"name"`
    Email string `json:"email" model:"index"`
}

db := service.Model()
db.Register(&User{})
db.Create(ctx, &User{ID: "1", Name: "Alice", Email: "[email protected]"})

var results []*User
db.List(ctx, &results, model.Where("email", "[email protected]"))

Backends: memory (default), SQLite, Postgres.

AI Providers

Swap providers with a single import — same interface everywhere:

ProviderDefault Model
Anthropicclaude-sonnet-4-20250514
OpenAIgpt-4o
Google Geminigemini-2.5-flash
Groqllama-3.3-70b-versatile
Mistralmistral-large-latest
Together AILlama-3.3-70B-Instruct-Turbo
Atlas Cloudllama-3.3-70b
go
m := ai.New("anthropic", ai.WithAPIKey(key))
resp, _ := m.Generate(ctx, &ai.Request{Prompt: "hello"})

Examples

See all examples.

Docs

Package reference: https://pkg.go.dev/go-micro.dev/v5