Google Agent Development Kit
Code-first Python toolkit for building and deploying Gemini-native agents
View on GitHubWhat it solves
Deploying agent systems to Google Cloud without manually stitching together Vertex AI, Gemini, and Cloud Run APIs: ADK makes them first-class citizens of the agent runtime.
Overview
Google's open-source framework for building agents that run on Vertex AI and deploy to Google Cloud. Uses a graph-based workflow model where each node is a callable agent step, with support for agent-to-agent (A2A) delegation and deep Gemini integration. Released in April 2025.
Key facts
- Language
- Python
- License
- Apache 2.0
- Maturity
- Fast-moving
- Maintainer
- Reviewed
- 2026-06-11
Where to start
The samples directory shows end-to-end agent patterns from single-step tools to multi-agent delegation flows.
contributing/samples/README.mdTechnologies
More in this domain
LangGraph
Stateful multi-agent orchestration for LLM applications
The state management problem in multi-agent systems: how you build agents that pass context across turns without losing the execution thread.
AutoGen
Multi-agent conversation framework from Microsoft Research
How to coordinate multiple specialized agents toward a shared goal without writing low-level orchestration logic by hand.
CrewAI
Role-based multi-agent orchestration for collaborative task execution
The boilerplate problem in multi-agent setup: defining roles, delegation rules, and task routing without writing a custom orchestration graph.