# micro/go-micro

A Go agent harness and service framework

Repository: https://github.com/micro/go-micro
Canonical: https://ross.abutalabs.com/products/go-micro
Homepage: https://go-micro.dev
Language: Go
License: Apache-2.0
License Family: permissive
Topics: go, golang, micro, microservices, distributed-systems, ai, ai-agents, mcp
Last push: 2026-08-25T06:03:58+00:00

## Health v2 (maintenance only)
Score: 95/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 100
- inputs: {"age_days": 4250, "days_push": 8, "days_rel": 8, "gap_med": 1.0, "n_releases_24m": 63}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 23043, forks 2418 (observed 2026-08-28T04:11:34.359833+00:00)

## What it is
Go Micro is a Go framework and CLI that combines an AI agent harness with a microservices framework, giving agents tools, memory, guardrails, planning, and service discovery on one runtime. Service endpoints automatically become AI-callable tools via MCP, agents are reachable over the A2A protocol, and deterministic work is orchestrated with durable, checkpointed flows.

## Use cases
- build AI agents in Go with tools and memory
- expose microservice endpoints as MCP tools for LLMs
- generate services from a natural language prompt
- orchestrate multi-agent workflows with durable flows
- make agents discoverable via the A2A protocol
- scaffold and hot-reload microservices locally with a CLI
- build a chatbot that talks to backend services

## When to choose
- you're building agents or agent-backed services in Go
- you want MCP/A2A interoperability out of the box
- you need a batteries-included microservices runtime with pluggable discovery, RPC, and pub/sub
- you want deterministic workflows that hand off to LLM agents

## When to avoid
- you need a lightweight agent library without a full service framework
- your stack is Python or TypeScript rather than Go
- you want a minimal HTTP framework without AI/agent features
- you need a very mature, conservative framework — the agent features are new and evolving

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rpc, mcp, web-framework, workflow-automation, chatbot, llm-inference, middleware, service-discovery, cli
- domain: microservices, large-language-models, backend, developer-tools, apis
- platform: go, windows, cli, self-hosted
- tags: agent-harness, a2a-protocol, mcp-gateway, services-as-tools, durable-workflows, code-generation, microservices-framework, pluggable-architecture, ai-agents, automation, linux, macos, docker

## Member repositories
- micro/go-micro (main) score 95

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:34.359833+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:56:48.927780+00:00, confidence not recorded.
  - readme: https://github.com/micro/go-micro (fetched 2026-08-28T04:11:34.359833+00:00, sha ae6ee06153d9)
  - homepage: https://go-micro.dev (fetched 2026-08-29T07:54:49.386747+00:00, sha 5139b4350f5c)
  - site_page: https://go-micro.dev/docs/index.html (fetched 2026-08-29T07:54:49.396069+00:00, sha 143bcdcf8f96)
  - site_page: https://go-micro.dev/docs (fetched 2026-08-29T07:54:49.398697+00:00, sha 3654a2179d55)
  - site_page: https://go-micro.dev/docs/getting-started.html (fetched 2026-08-29T07:54:49.402548+00:00, sha 4b1e88b82a12)
  - site_page: https://go-micro.dev/blog/2026/06/05/introducing-micro-newagent.html (fetched 2026-08-29T07:54:49.400623+00:00, sha efeb29f55ae2)
- Data as of 2026-08-30T08:39:29.467469+00:00.
