google/adk-go

An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 42 minutes ago
Added to GitGenius on November 18th, 2025
Created on May 5th, 2025
Open Issues & Pull Requests: 326 (+0)
Number of forks: 971
Total Stargazers: 8,692 (+0)
Total Subscribers: 103 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 27.4 hours
Mean response time: 8.5 days
90th percentile: 19.1 days
Tracked items: 259

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 91% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 31% of tracked open issues have had no activity in three months. Only 5% of issues opened in the past year have been closed. Three people close 52% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 122
New in 7 days: 14
Closed in 7 days: 9
Avg open age: 71 days
Stale 30+ days: 88
Stale 90+ days: 39

Recent activity

Opened in 7 days: 6
Closed in 7 days: 9
Comments in 7 days: 14
Events in 7 days: 65

Top labels

  • bug (127)
  • enhancement (78)
  • needs review (30)
  • api (12)
  • documentation (8)
  • good first issue (8)
  • question (7)
  • breaking change (6)

Detailed Description

The Agent Development Kit (ADK) for Go is an open-source framework developed by Google for building, evaluating, and deploying sophisticated AI agents using Go. It represents a code-first approach to agent development, allowing developers to define agent logic, tools, and orchestration directly in Go code rather than through configuration files or visual interfaces. The toolkit is designed to be idiomatic to Go, leveraging the language's strengths in concurrency and performance, making it particularly well-suited for cloud-native agent applications.

ADK for Go is part of a larger ecosystem that includes Python, Java, and web versions of the toolkit, all sharing similar design principles but tailored to their respective languages and use cases. While optimized for integration with Google's Gemini models and Vertex AI, the framework is model-agnostic and deployment-agnostic, allowing developers to work with various language models and deploy to different environments. The toolkit emphasizes flexibility and control, enabling developers to build everything from simple agent tasks to complex multi-agent systems.

The framework provides several key features that distinguish it as a comprehensive agent development solution. It includes a rich ecosystem of pre-built tools that agents can utilize, while also supporting custom functions and integration with existing tools to give agents diverse capabilities. The modular architecture enables developers to design scalable applications by composing multiple specialized agents that can work together, supporting multi-agent collaboration and orchestration patterns. Deployment is simplified through strong support for containerization and cloud-native environments, particularly Google Cloud Run, though agents can be deployed to various platforms.

Repository activity data shows active maintenance and community engagement.

The repository is classified across multiple technical domains including app development, Go programming, device connectivity, accessory development, hardware interaction, embedded systems, USB communication, protocol implementation, peripheral control, and SDK development. This broad classification reflects the toolkit's versatility and its applicability across different types of agent applications. The codebase is licensed under Apache 2.0, with an exception for the internal httprr component which maintains its own license file. The project maintains comprehensive documentation at google.github.io/adk-docs and provides sample implementations in the examples directory, supporting developers in getting started with the framework.