Google Agent Development Kit (ADK)
Code-first agent framework from Google
The Agent Development Kit (ADK) is an open-source framework from Google for building, evaluating and deploying agents in code. It is available for Python, TypeScript, Go, Java and Kotlin and offers workflow agents for sequential, parallel and loop flows, plus graph-based workflows since version 2.0. ADK is optimized for Gemini but also works with Claude, OpenAI models and local models; deployment targets include Agent Runtime, Cloud Run and GKE.
Good fit if
Focus: Developers who want to run agents on Google Cloud or with Gemini without locking into one model
- your project is about Hierarchical multi-agent systems, Agents on Google Cloud or Agent evaluation
- someone on your team writes code
Probably not if
- nobody on your team writes code (1/5 for use without developers)
Key figures
- Usable without developers
- 1/5
- Scalability
- 5/5
- Integrations
- 4/5
- Versioning
- 3/5
- Observability
- 4/5
Editorial rating on a scale from 1 to 5. Methodology
Fact sheet
- Category
- Developer
- Type
- Code-first agent framework from Google
- Licence
- Open Source (Apache-2.0)
- Pricing
- Open SourceFramework free (Apache 2.0). Costs arise from model APIs and the chosen runtime.
- Deployment
- Self-Hosted, GCP Cloud, Cloud, Kubernetes
- Models
- Google (Gemini, Gemma), Anthropic, OpenAI, Ollama, vLLM, LiteLLM
- RAG
- Yes
- Multi-Agent
- Yes
- SSO, roles (RBAC)
- SSO no, RBAC no
- Latest version
- 2.11.0 (Python)
- GitHub stars
- 21,800
Key features
- Workflow agents (sequential, parallel, loop)
- Graph-based workflows
- A2A and MCP
- Built-in evaluation
- Multiple programming languages
Typical use cases
- Hierarchical multi-agent systems
- Agents on Google Cloud
- Agent evaluation
- Cross-agent communication via A2A
Sources
- Dokumentation(opens in a new tab)
- GitHub (Python)(opens in a new tab)
- GitHub (Java)(opens in a new tab)
Checked on 9 Oct 2026
Implementation
Get Google Agent Development Kit (ADK) implemented
Free for you. Partners only pay for requests they accept.
Alternatives
Similar systems
Similar in category, features or use cases.
- DeveloperMicrosoft Agent FrameworkMicrosoft Agent Framework is Microsoft's open-source framework for agents and multi-agent workflows in Python and .NET. Version 1.0 shipped in April 2026 and is the unified successor of Semantic Kernel and AutoGen. A graph-based workflow engine supports branching, parallelism, checkpoints and human approvals; ready-made patterns exist for sequential, concurrent, handoff, group chat and Magentic-One orchestration. MCP and A2A are supported.View profile
- DeveloperCrewAICrewAI is a Python framework for teams of agents with defined roles, goals and tasks. Crews work through tasks sequentially or hierarchically, while Flows control event-driven, stateful processes. The framework is MIT licensed; for deployment, monitoring and management CrewAI offers the commercial platform CrewAI AMP.View profile
- DeveloperInngest AIInngest is an event-driven durable execution platform: functions consist of steps that are retried automatically on failure and resumed after interruptions. For AI applications Inngest offers AgentKit and steps for LLM calls, so multi-step agents run reliably without operating your own queues. The server and CLI are licensed under the SSPL with delayed publication under Apache 2.0, the SDKs under Apache 2.0.View profile
- DeveloperMetaGPTMetaGPT is a multi-agent framework that assigns different roles to GPTs to form a collaborative software entity for complex tasks. It automates the entire software development process from requirements to documentation. The system is characterized by end-to-end automation with a single input, multi-AI role collaboration (product managers, architects, project managers, engineers), and standardized operating procedures (SOPs).View profile