Ingenimax/agent-sdk-go

A powerful Go framework for building production-ready AI agents!

Ingenimax / agent‑sdk‑go – Go SDK for building AI agents

What it is

  • A Go library (and accompanying CLI) that lets you assemble production‑grade AI agents. It wraps large‑language‑model (LLM) providers (OpenAI, Anthropic, Google Vertex AI) and adds a toolbox of features that are common in enterprise‑level agents: persistent memory, tool calling, multi‑agent orchestration, guardrails, observability, and multi‑tenant isolation.

Key capabilities

Area What the SDK provides
LLM integration Plug‑and‑play clients for OpenAI, Anthropic, Gemini; token‑usage reporting; model‑context‑protocol (MCP) support over HTTP/SSE or stdio.
Memory Conversation buffer, vector‑based retrieval, summarisation, consolidation of facts, and durable storage back‑ends (in‑memory, SQLite, Postgres, Redis).
Tools Built‑in web‑search tool, calculator, and a registry for custom tools. Tools are invoked automatically by the agent when needed.
Agent orchestration Define agents in YAML, compose them in sequential, parallel, loop or graph patterns, and let a model transfer a conversation to a more suitable sub‑agent.
Enterprise features Guardrails for safety, tracing/logging, multi‑tenant isolation, hook/plugin system to audit or rewrite tool calls, background run management, and token‑cost tracking.
Developer experience Declarative YAML configuration, auto‑generated agent setups from system prompts, structured‑task framework, versioned evaluation datasets with JSON/JUnit reports.

How you use it

  1. Add the library – go get github.com/Ingenimax/agent-sdk-go.
  2. Create an LLM client (e.g., openai.NewClient(apiKey)).
  3. Register tools via tools.NewRegistry() and optionally add the built‑in web‑search tool.
  4. Instantiate an agent with agent.NewAgent, passing the LLM, memory, tools, system prompt, etc.
  5. Run the agent – call agent.Run(ctx, "your query") or start an interactive chat with the provided agent-cli.

Configuration

  • Environment variables (e.g., OPENAI_API_KEY, REDIS_ADDRESS) drive the SDK.
  • Full YAML schemas let you describe agents, tasks, memory back‑ends, MCP servers, and even response JSON schemas.
  • Example YAML shows hierarchical agents, sub‑agents, and runtime settings.

CLI

  • agent-cli init creates a starter config.
  • agent-cli run "question" executes a single query.
  • agent-cli chat opens an interactive REPL.
  • The CLI can be installed from pre‑built binaries, go install, or built locally with make build-cli.

Ecosystem

  • Documentation site: https://docs.goagents.dev/
  • An AI assistant named Nina can be connected via MCP for in‑IDE help (Cursor, Claude Desktop).
  • The project supports optional Redis for distributed memory and offers hooks for custom auditing.

Who it’s for

  • Go developers who need a ready‑made framework to build chat‑based assistants, research bots, or any workflow that combines LLM reasoning with external tools.
  • Teams looking for enterprise‑grade features (multi‑tenant, guardrails, observability) without wiring everything from scratch.

Bottom line Ingenimax’s agent‑sdk‑go is a comprehensive, production‑focused Go toolkit for constructing, configuring, and running AI agents that can call tools, remember context, and operate safely at scale.

Related

  • Project
    microsoft/agent-framework-go

    Microsoft Agent Framework for Go is a production‑grade SDK that lets Go developers build, orchestrate, and observe multi‑agent AI workflows. It supports multiple LLM providers (Azure OpenAI, OpenAI, Microsoft Foundry), middleware, graph‑based workflow patterns, OpenTelemetry tracing, and skill‑based knowledge bases. The repo includes install instructions, a quick‑start haiku example, and a rich set of sample projects. It’s in public preview and aligns with the broader MAF ecosystem (.NET/Python).

  • 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
    micro/go-micro

    A Go framework for building distributed services and AI agents that allows agents to use registered services as tools to carry out work.

  • Project
    Lamatic/AgentKit

    AgentKit is an open‑source SDK that provides a catalog of 70 ready‑made “kits” (full apps, pipelines, or templates) for building, testing and deploying AI agents. Kits are defined by a simple config file, can be edited in a visual flow studio, and are shipped as Next.js apps that run server‑less. The collection covers support triage, code review, RAG chat, hiring assistants, legal/medical bots, and many other business‑focused agents, making it a turnkey platform for creating reliable, enterprise‑grade AI agents.

  • Project
    a2aproject/a2a-go

    A Go library for building and consuming AI‑style agents that follow the open Agent‑to‑Agent (A2A) protocol, with client/server APIs, support for gRPC/REST/JSON‑RPC, and extensible plug‑in points.