Codex
aad0c0c8a1
3.9 KiB
layout
| layout |
|---|
| default |
Docs
Documentation for the Go Micro agent harness and service framework.
Overview
Go Micro is an agent harness and service framework for Go. A harness is the runtime around an agent: tools, memory, guardrails, workflows, state, discovery, and interop. Build an agent and it gets a model, memory, tools, planning, delegation, and service discovery; it is reachable over MCP and A2A. Write services and every endpoint becomes an AI-callable tool. Orchestrate the deterministic parts with durable flows. Agents, services, and flows come from the same primitives because an agent is a distributed system, and building one is building a service.
It's built on a pluggable architecture of Go interfaces: service discovery, client/server RPC, pub/sub, plus auth, caching, and storage. Sane defaults out of the box, everything swappable.
Learn More
Start with Getting Started for install and the first local service. Then follow the first-agent on-ramp: No-secret first-agent transcript to run a mock-model support agent, Your First Agent to build and chat with a service-backed agent, Debugging your agent to inspect runs and memory, and the 0→hero reference path to walk the full scaffold → run → chat → inspect → deploy dry-run lifecycle covered by CI.
Otherwise continue to read the docs for more information about the framework.
Contents
- Getting Started
- 0→hero Reference - Walk scaffold → run → chat → inspect → deploy dry-run with CI-backed commands
- No-secret first-agent transcript - Run the first useful agent path without a provider key
- Your First Agent - Build a service-backed agent end to end
- MCP & AI Agents - Turn services into AI-callable tools with the Model Context Protocol
- CLI & Gateway Guide - Development vs Production modes
- Quick Start
- Architecture
- Configuration
- Registry
- Broker
- Client/Server
- Transport
- Store
- Plugins
- Examples
Development & Deployment
- micro run - Local development with hot reload, API gateway, and agent playground
- micro build & deploy - Build binaries and deploy to production
- micro server - Optional production web dashboard with auth
AI & Agents
- 0→hero Reference - Walk scaffold → run → chat → inspect → deploy dry-run with CI-backed commands
- No-secret first-agent transcript - Run the first useful agent path without a provider key
- Your First Agent - Build a service-backed agent end to end
- Building AI-Native Services - End-to-end tutorial for MCP-enabled services
- MCP Security Guide - Auth, scopes, rate limiting, and audit logging
- Tool Description Best Practices - Writing docs that make agents effective
- Agent Integration Patterns - Multi-agent harness patterns and architectures