An open-source, code-first C# (Dotnet) toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
# Agent Development Kit (ADK) for .NET (C#)
[](LICENSE.md)
[](#-installation)
<html>
<h2 align="center">
<img src="https://raw.githubusercontent.com/google/adk-python/main/assets/agent-development-kit.png" width="256"/>
</h2>
<h3 align="center">
An open-source, code-first .NET toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
</h3>
</html>
Agent Development Kit (ADK) is designed for developers seeking fine-grained
control and flexibility when building advanced AI agents that are tightly
integrated with services in Google Cloud. It allows you to define agent
behavior, orchestration, and tool use directly in code, enabling robust
debugging, versioning, and deployment anywhere – from your laptop to the cloud.
---
> **⚠️ EXPERIMENTAL** - This project is in active development and the API will change. Builds are nightly and super frequent and may contain breaking changes. Use in production at your own risk.
## ✨ Key Features
### 🧠 Intelligence & Models
- **Model Backends**: Support for **Gemini** (`GoogleAdk.Models.Gemini`) and **MEAI** (`GoogleAdk.Models.Meai`) for providers like Ollama. [More info](docs/models.md).
- **Planning**: Equip agents with ReAct-style planners via natural-language processing. [More info](docs/planning.md).
- **Caching**: Prompt and context caching using Gemini-backed implicit caching. [More info](docs/caching.md).
### 🛠️ Tools & Integrations
- **C# Source Gen Tools**: Effortlessly turn methods into tools using the `[FunctionTool]` attribute. [More info](docs/tools.md).
- **MCP Support**: Full Model Context Protocol integration with dynamic tool discovery. [More info](docs/mcp.md).
- **OpenAPI Integration**: Generate tools seamlessly from OpenAPI specs.
- **Code Execution**: Run generated code within secure environments.Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.