adk-python and awesome-google-adk
One project is a Python toolkit for building AI agents, while the other is a curated list of resources, including the former, for Google's Agent Development Kit, making them complements within the ecosystem.
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 awesome-google-adk
tsubasakong/awesome-google-adk
A curated list of awesome resources for Google's Agent Development Kit (ADK)
Organizes official Python implementations, multi-agent frameworks, and integrations—including UI builders, domain-specific applications, and model connectors—across Google Cloud, Anthropic, AWS Bedrock, and MCP servers. Covers architectural patterns like agent-to-agent communication (A2A), streaming protocols, and production deployment templates alongside step-by-step tutorials for building scalable agentic systems.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work