micro/go-micro

A framework for agents, tools and services

What it solves

Go Micro is a framework for building distributed services and AI agents in Go. It simplifies the process of creating services that provide specific capabilities and connecting them as tools for AI agents to discover and use to perform complex tasks.

How it works

The framework operates on a core set of pluggable interfaces for RPC, discovery, and pub/sub. It integrates AI models via a common interface, allowing agents to interpret requests and use registered services as tools. It also supports workflows to coordinate repeatable sequences of work involving both service calls and agent decisions.

Who it’s for

Go developers who want to build agentic systems where AI agents can interact with a set of independent, distributed services to carry out work.

Highlights

  • Service-backed Agents: Agents can be given capabilities by selecting registered services, which effectively turn those services' endpoints into the agent's tools.
  • Integrated CLI: A dedicated CLI allows users to chat with agents or use a development agent to generate, build, and start services.
  • Pluggable Architecture: Core components like registry, client/server, broker, and transport are independently usable.
  • Workflow Coordination: Provides tools to coordinate defined steps between service calls and agent decisions.

Related

  • Project
    Ingenimax/agent-sdk-go

    A Go SDK (and CLI) for building production‑ready AI agents with multi‑LLM support, persistent memory, tool integration, multi‑agent orchestration, guardrails, and enterprise features, configurable via environment variables or rich YAML files.

  • Project
    smallnest/pigo

    pigo is a Go‑based CLI AI coding assistant (a clone of the pi agent) that can read/write files, run shell commands, fetch web content, and interact with many LLM providers. It works in headless script mode or an interactive REPL, supports tool‑level allow/deny lists, project trust, prompt templates, skills, plugins, self‑update, and provides a Go SDK for embedding.

  • Dispatch
    Building an AI Agent CLI with Go Micro

    The Go Micro team demonstrates how to build a tool-calling AI agent CLI in approximately 150 lines of code by leveraging self-describing services and a uniform model interface.

  • Project
    trpc-group/trpc-agent-go

    A Go-native framework for building production AI agent systems with support for graph workflows, multi-agent collaboration, persistent memory, and self-evolving skills.

  • Project
    GizClaw/flowcraft

    A modular Go toolkit for building provider-agnostic AI applications with support for long-term memory, durable agent execution, and MCP-based plugins.