Agenten & Multi-Agenten

Agent Development Kit (ADK) 2.0 by Google

google/adk-python

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

Offizielles Repository öffnen ↗ Projekt-Startseite ↗
★ 21KSterne
⑂ 3,8KForks
554Offene Issues
PythonSprache
Apache-2.0Lizenz
Q@project.QualityScoreRedaktionelle Bewertung

Projekt-Screenshots

Screenshot von Agent Development Kit (ADK) 2.0 by Google Screenshot von Agent Development Kit (ADK) 2.0 by Google Screenshot von Agent Development Kit (ADK) 2.0 by Google Screenshot von Agent Development Kit (ADK) 2.0 by Google Screenshot von Agent Development Kit (ADK) 2.0 by Google Screenshot von Agent Development Kit (ADK) 2.0 by Google

Übersicht

Google's Agent Development Kit (ADK) is a Python-based framework designed for creating agentic applications. Version 2.0 introduces a graph-based Workflow Runtime for deterministic execution flows and a Task API for structured agent-to-agent delegation. It allows developers to define individual AI agents and orchestrate them using workflows, supporting complex routing, loops, and human-in-the-loop interactions.

Wichtige Funktionen

  • Code-first Python toolkit
  • Graph-based Workflow Runtime
  • Task API for structured agent-to-agent delegation
  • Support for routing, fan-out/fan-in, loops, and nested workflows
  • Human-in-the-loop capabilities
  • Interactive CLI and Web UI for local running
  • Bi-weekly release cadence

Voraussetzungen, Installation und Schnellstart

Install the core package using pip: `pip install google-adk`. For transitive dependency protection, it is recommended to download and use the constraints file matching your Python version (e.g., `curl -o constraints-3.10.txt https://raw.githubusercontent.com/google/adk-python/main/constraints-3.10.txt` and `pip install google-adk -c constraints-3.10.txt`). Optional integrations can be installed via `pip install "google-adk[extensions]"`.

Nutzung

Define an agent by instantiating the `Agent` class with a name, model, and instruction. Define a `Workflow` by specifying edges that connect agents in a graph. Run applications locally using the command line interface (`adk run path/to/my_agent`) or launch a web interface (`adk web path/to/agents_dir`).

Modellkompatibilität und Anwendungsfälle

The repository demonstrates usage with the 'gemini-2.5-flash' model. Specific supported model lists are not stated in the repository metadata.

Lizenz- und Risikohinweise

Licensed under the Apache 2.0 License.

Editorial verification 2026-08-09: repository URL, owner, description, license and repository statistics were reviewed. License metadata: Apache-2.0. README was fetched for the channel draft; re-check repository dependencies, releases and model terms before production use.

Veröffentlichung und Wartung

Version 2.0 introduces the Workflow Runtime (graph-based execution engine) and the Task API (structured agent-to-agent delegation). The project follows a roughly bi-weekly release cadence.

Firecrawl

firecrawl/firecrawl

★ 161,1KTypeScript

LangChain

langchain-ai/langchain

★ 143,6KPython

RAGFlow

infiniflow/ragflow

★ 86,7KGo