Dwij
a3354e3861
* feat: add Observability section to mkdocs configuration and Agentops integration This commit introduces a new "Observability" section in the mkdocs.yml file, including a link to the AgentOps Integration documentation. This enhancement improves the navigation structure of the documentation. * small docs revisions * Alex updates * Update agentops.md * fix: update navigation label for AgentOps in mkdocs.yml * Update agentops.md * Update README.md * Update README.md * Update mkdocs.yml --------- Co-authored-by: Braelyn Boynton <bboynton97@gmail.com> Co-authored-by: Alex Reibman <meta.alex.r@gmail.com> Co-authored-by: Sita Lakshmi Sangameswaran <sitalakshmi@google.com>
2.7 KiB
Agent Development Kit (ADK)
An open-source, code-first toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Agent Development Kit (ADK) is a flexible and modular framework for developing and deploying AI agents. While optimized for Gemini and the Google ecosystem, ADK is model-agnostic, deployment-agnostic, and is built for compatibility with other frameworks. ADK was designed to make agent development feel more like software development, to make it easier for developers to create, deploy, and orchestrate agentic architectures that range from simple tasks to complex workflows.
✨ Key Features
-
Rich Tool Ecosystem: Utilize pre-built tools, custom functions, OpenAPI specs, or integrate existing tools to give agents diverse capabilities, all for tight integration with the Google ecosystem.
-
Code-First Development: Define agent logic, tools, and orchestration directly in Python and Java for ultimate flexibility, testability, and versioning.
-
Modular Multi-Agent Systems: Design scalable applications by composing multiple specialized agents into flexible hierarchies.
-
Tracing and Monitoring: Built-in agent observability for debugging and optimizing workflows with support from external providers like AgentOps.
-
Deploy Anywhere: Easily containerize and deploy agents on Cloud Run or scale seamlessly with Vertex AI Agent Engine.
🚀 Installation
You can install the Agent Development Kit (ADK) using your preferred package manager for Python or build tool for Java.
For Python (pip)
pip install google-adk
For Java (Maven)
<dependency>
<groupId>com.google.adk</groupId>
<artifactId>google-adk</artifactId>
<version>0.1.0</version>
</dependency>
For Java (Gradle)
dependencies {
implementation 'com.google.adk:google-adk:0.1.0'
}
📚 Documentation
Explore the full documentation for detailed guides on building, evaluating, and deploying agents:
🤝 Contributing
We welcome contributions from the community! Whether it's bug reports, feature requests, documentation improvements, or code contributions, please see our Contributing Guidelines to get started.
📄 License
This project is licensed under the Apache 2.0 License - see the LICENSE file for details.
Happy Agent Building!