adk-python and adk-go
About adk-python
google/adk-python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Supports model-agnostic agent development with built-in integration for Gemini, MCP tools, and OpenAPI specs, plus hierarchical multi-agent orchestration where coordinator agents delegate to specialized sub-agents. Features a modular architecture enabling deployment to Cloud Run or Vertex AI Agent Engine, with a built-in development UI for testing and an evaluation framework for benchmarking agent performance. Includes session management capabilities like rewinding invocations and tool confirmation flows for human-in-the-loop control.
About adk-go
google/adk-go
An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Provides a modular, multi-agent framework with built-in tool ecosystems and custom function integration, optimized for Go's concurrency model. Model-agnostic architecture works across Gemini and other LLMs, with first-class support for cloud-native deployments like Google Cloud Run. Code-first approach enables agents to be defined, tested, and versioned directly in Go with seamless orchestration of specialized agent workflows.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work