HomeProjectsArticlesPK BoardAbout
Explore Projects

Agent Development Kit

Active
GitHub Python Apache-2.0

Description

Google Agent Development Kit (ADK) is Google's agent development framework for building complex AI agent systems with tool integration and multimodal processing capabilities.

Key Features

  • Graph-based workflow runtime with routing, fan-out/fan-in, loops, retry, and state management
  • Structured Task API for agent-to-agent delegation with multi-turn and single-turn modes
  • Human-in-the-loop support at both workflow and task delegation levels
  • Code-first Python framework with flexible agent composition and evaluation tools
  • Built-in Web UI and interactive CLI for local agent testing
  • Extensible integration system via optional extensions package

Use Cases

💡 Building complex multi-agent systems with deterministic execution flows
💡 Creating AI applications requiring human oversight and approval gates
💡 Developing agentic workflows with tool integration and multimodal processing
💡 Rapid prototyping and evaluation of conversational AI agents

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (21.4k stars)
  • • Permissive open-source license (Apache-2.0)

Tags

agent-framework google llm python

Categories

🤖 Agent Framework

Quick Start

pip install google-adk && adk web path/to/agents_dir
Visit GitHub Visit Website

Related Projects

AutoAgent

9.8k · Python
Stale B

Fully-automated and zero-code LLM agent framework that enables users to build and deploy custom AI agents through natural language without writing code.

agent-frameworkzero-codeautomation +2
  • · Fully-automated agent building through natural language — no coding required to create, customize, and deploy AI agents
  • · Zero-code framework democratizing AI development for users without technical backgrounds
  • · Self-managing workflow generation that dynamically creates and optimizes agent pipelines from high-level descriptions
View full details → View on GitHub

ART

10.7k · Python
Active A+

ART (Agent Reinforcement Trainer) trains multi-step agents for real-world tasks using GRPO reinforcement learning, enabling on-the-job training for models like Qwen, Llama, and more.

reinforcement-learningagent-trainingGRPO +3
  • · GRPO-based reinforcement learning for training multi-step agents on real-world tasks
  • · W&B Training serverless RL with 40% lower cost and 28% faster training via shared inference cluster
  • · Pre-built notebooks for email search, 2048, Tic Tac Toe, Codenames, and MCP tool mastery
View full details → View on GitHub

PocketFlow

11.1k · Python
Normal A

PocketFlow is a minimalist 100-line LLM framework that lets Agents build Agents, enabling complex AI agent workflows through a clean abstraction layer.

agent-frameworkllmworkflow +2
  • · Only 100 lines of code, zero dependencies, zero vendor lock-in — ultra lightweight
  • · Graph-based abstraction supporting Agent, Multi-Agent, Workflow, and RAG design patterns
  • · Supports Agentic Coding — let AI agents like Cursor build agents for 10x productivity
View full details → View on GitHub

Related Articles

AI Agent框架对比LangChain

Best AI Agent Frameworks in 2026: LangGraph vs CrewAI vs OpenAI Agents SDK vs Google ADK Compared

A practical 2026 comparison of the top AI agent frameworks — LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, Google ADK, Microsoft Agent Framework, Mastra, and Claude Agent SDK. Covers architecture philosophy, production maturity, multi-language support, observability, and team fit, with a selection decision tree.

Read more →
Google ADKGeminiVertex AI

Google ADK (Agent Development Kit) in Practice: A2A Protocol, Vertex AI Integration, and Java Dual-Language

Google ADK is Google's official agent SDK with dual-language Python and Java support and deep integration with Vertex AI and the Gemini models. This article walks through ADK's four cores — Agent, Tool, Session, and the A2A protocol — compares it with LangGraph, OpenAI Agents SDK, and Claude Agent SDK, and provides an enterprise deployment path.

Read more →