Skip to content

Rustic AI Agents Documentation

Welcome to the Rustic AI Agents documentation. This section provides detailed information about the agents available in the Rustic AI framework.

What is an Agent?

In Rustic AI, an agent is a specialized component that performs specific tasks within a guild (multi-agent system). Each agent:

  • Processes specific types of messages
  • Maintains its own state
  • Can interact with external services
  • Communicates with other agents through a message-based system

Available Agents

Rustic AI includes several specialized agents for various tasks:

LLM Agent Framework

  • LLM Agent & Plugin System - Comprehensive LLM agent with extensible plugin system for request/response processing and dependency injection
  • LLM Agent Memory Stores - Memory systems for conversation history, state persistence, and semantic recall
  • LLM Agent Plugins - Plugin architecture for preprocessing, postprocessing, and tool call interception
  • ReAct Agent - Reasoning and Acting agent that iteratively uses tools to solve complex tasks

Web and API Agents

External Tool Integration

  • MCP Integration - Connect to MCP (Model Context Protocol) servers for external tools

Language Model Agents

AI Media Generation

NLP Agents

Utility Agents

  • VectorAgent - Document indexing and similarity search
  • KnowledgeAgent - Advanced knowledge base indexing with chunking, embedding pipelines, and hybrid search
  • ProbeAgent - Testing utility for monitoring agent interactions

System Agents

Skills and Toolsets

Rustic AI provides a powerful skills framework that enables agents to use pre-built, reusable capabilities:

Creating Custom Agents

For guidance on creating your own agents, see the Creating Your First Agent guide.