#2424th of 33 in Agent frameworks and SDKs
adk-python
Code-first Python framework for building, evaluating and deploying multi-agent apps
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 21.8k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
ADK is Google's Python framework for defining agents and graph-based workflows in code, with tool calling (custom functions, OpenAPI specs, MCP), multi-agent hierarchies and a Task API for agent-to-agent delegation. It ships a CLI (`adk run`, `adk web`, `adk eval`, `adk deploy`) and a built-in dev UI. Optimized for Gemini but described as model-agnostic; deploy targets include Docker, Cloud Run and Vertex AI Agent Engine.
Who it is for: Python developers building and deploying multi-agent LLM applications
Strengths
- Graph-based Workflow runtime with routing, fan-out/fan-in, loops, retry and human-in-the-loop
- Built-in CLI for running, evaluating (`adk eval`) and deploying agents
- Dev web UI included for testing and debugging agents
- Tool confirmation flow guards tool execution; MCP and OpenAPI tools supported
Weaknesses
- Optimized for Gemini and Google Cloud; other model providers are not enumerated in the README
- Requires Python 3.11 or newer
- Roughly bi-weekly releases; main branch may contain experimental changes
- Managed scaling path points to Vertex AI Agent Engine, a Google Cloud service
What it needs
- no GPU
- Needs Python 3.11+, Gemini API or Vertex AI (default models), Docker (optional, for deploy), Google Cloud Run (optional)
- Models: Gemini, model-agnostic (providers unknown)
Also in Agent frameworks and SDKs
See all 33| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 92 out of 100 |
| 2 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| 3 | browser-usePython library that lets an LLM agent control a web browser | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 87 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 84 out of 100 |