ADK-Rust Official Documentation
Welcome to the official documentation for ADK-Rust (Agent Development Kit for Rust). This documentation provides comprehensive guides and references for building AI agents using the Rust implementation of the ADK framework.
Getting Started
- Introduction - Overview of ADK-Rust, its architecture, and key concepts
- Quickstart - Build your first agent in under 10 minutes
Core
- Core Types - Fundamental types: Content, Part, Agent trait, Tool trait, contexts
- Runner - Agent execution runtime and configuration
Models
- Model Providers - LLM integrations: Gemini, OpenAI, Anthropic, DeepSeek, Groq, Ollama
- Ollama - Local inference with Ollama
- mistral.rs Integration - Native mistral.rs for high-performance local inference
Agents
- LlmAgent - The core agent type using Large Language Models
- Workflow Agents - Deterministic agents: Sequential, Parallel, Loop
- Multi-Agent Systems - Building agent hierarchies with sub-agents
- Graph Agents - LangGraph-style workflow orchestration
- Realtime Agents - Voice-enabled agents with OpenAI/Gemini
Tools
- Function Tools - Create custom tools with async Rust functions
- Built-in Tools - Pre-built tools like GoogleSearchTool
- MCP Tools - Model Context Protocol integration
- Browser Tools - 46 WebDriver tools for web automation
- UI Tools - Dynamic UI generation with forms, cards, charts
Sessions & State
- Sessions - Session management and lifecycle
- State Management - Managing conversation state with prefixes
Callbacks & Events
- Callbacks - Intercept and customize agent behavior
- Events - Understanding the event system and conversation history
Artifacts
- Artifacts - Binary data storage and retrieval
Observability
- Telemetry - Logging, tracing, and monitoring
Deployment
- Launcher - Running agents in console or server mode
- Server - REST API and web UI integration
- A2A Protocol - Agent-to-Agent communication
Evaluation
- Agent Evaluation - Testing and validating agent behavior
Security
- Access Control - Role-based permissions and audit logging
- Guardrails - PII redaction, content filtering, schema validation
- Memory - Long-term semantic memory for agents
Studio
- ADK Studio - Visual development environment for building agents
Development
- Development Guidelines - Contributing guide and best practices
Validation Status
All code samples in this documentation are validated through working examples in the official_docs_examples/ packages. Each documentation page has corresponding examples that compile and execute successfully.