HomeProjectsArticlesPK BoardAbout
Explore Projects

Google ADK Go

Active
GitHub Go Apache-2.0

Description

An open-source, code-first Go toolkit by Google for building, evaluating, and deploying sophisticated AI agents with flexible tool integration, multi-turn conversation management, and streaming responses.

Key Features

  • Idiomatic Go design leveraging native concurrency and performance for cloud-native agent applications
  • Rich tool ecosystem with pre-built tools, custom functions, and external tool integration
  • Code-first development approach defining agent logic, tools, and orchestration directly in Go
  • Modular multi-agent systems enabling composition of multiple specialized agents
  • Deploy anywhere with containerization support and strong cloud-native integration (Google Cloud Run)
  • Model-agnostic framework optimized for Gemini but compatible with other LLMs

Use Cases

💡 Building cloud-native AI agent applications with Go's concurrency model
💡 Creating multi-agent orchestration systems for complex task workflows
💡 Deploying production-grade agent services on Google Cloud Run or Kubernetes
💡 Integrating custom tools and APIs into agent pipelines for enterprise automation

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (8.7k stars)
  • • Permissive open-source license (Apache-2.0)

Tags

go agent framework gemini llm sdk

Categories

🤖 Agent Framework

Quick Start

Install: go get google.golang.org/adk. Define your agent in Go code with tools and orchestration logic, then deploy to any cloud environment.
Visit GitHub Visit Website

Related Projects

AgentField

2.5k · Go
Active A

A framework for building, running, and scaling AI agents as APIs and microservices, with built-in observability, auditability, and identity-aware access control from day one.

goagentframework +3
  • · Build AI agents as REST endpoints with Python, Go, or TypeScript — no DSL or YAML required
  • · Cryptographic identity and tamper-proof audit trails for every agent execution
  • · Built-in human-in-the-loop with pause/resume for approval workflows via webhooks
View on GitHub

Spring AI

9.4k · Java
Active A

An application framework for AI engineering from the Spring team, providing unified LLM integration, vector storage, function calling, RAG, and agent development for Java and Spring ecosystems with support for OpenAI, Anthropic, Ollama, and more.

javaframeworkllm +6
  • · Official Spring AI engineering framework bringing Spring ecosystem portability and modular design to AI
  • · Unified API supporting all major AI model providers including OpenAI, Anthropic, Google, and Amazon
  • · Supports complete model types: chat completion, embedding, text-to-image, audio transcription, and text-to-speech
View full details → View on GitHub

WeKnora

21.2k · Go
Active A

Tencent's open-source LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG.

goragllm +3
  • · RAG-based Quick Q&A for everyday document lookups with semantic retrieval
  • · ReAct Agent autonomously orchestrating retrieval, MCP tools, and web search for complex multi-step tasks
  • · Wiki Mode where agents distill raw documents into self-maintaining, interlinked markdown knowledge bases with interactive knowledge graphs
View full details → View on GitHub

Agently

1.6k · Python
Active A

A GenAI application development framework that simplifies agent interaction with structured data and chained-calls syntax, using event-driven flow for complex logic.

agentpythonframework +1
  • · Structured output control with framework-guaranteed schemas, required field extraction, and retry validation
  • · Runtime Skills system for discovering, installing, and executing MCP/script capabilities on demand
  • · TriggerFlow event-driven workflows with fan-out, pause/resume, save/load, and sub-flow support
View on GitHub