adk-python and adk-extra-services
The first is a core framework for building AI agents, while the second extends it with optional third-party service integrations, making them complements designed to be used together.
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-extra-services
edu010101/adk-extra-services
A Python package providing additional service implementations for the Google ADK framework (S3, Redis, MongoDB, Azure, etc)
Provides pluggable session storage (MongoDB, Redis) and artifact management (S3, Azure Blob, Supabase) services that integrate directly with ADK agents through standardized interfaces. Supports multiple backend implementations for both features, enabling flexible deployment across cloud providers and local development environments. Built for production use with consistent APIs across storage backends.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work