Agents

Agents at Agno are the building blocks of your agentic system. They are autonomous AI programs that dynamically determine their course of action using a large language model. The core components of an Agent are:

Model: controls the flow of execution. It decides whether to reason, act or respond.
Instructions: are how we program the Agent, teaching it how to use tools and respond.
Tools: enable an Agent to take actions and interact with external systems.
Reasoning: enables Agents to “think” before responding and “analyze” the results of their actions (i.e. tool calls), this improves reliability and quality of responses.
Knowledge: is domain-specific information that the Agent can search at runtime to make better decisions and provide accurate responses (Retrieval-Augmented Generation, or RAG). Knowledge is stored in a vector database and this search at runtime pattern is known as Agentic RAG/Agentic Search.
Storage: is used by Agents to save session history and state in a database. Model APIs are stateless and storage enables us to continue conversations from where they left off. This makes Agents stateful, enabling multi-turn, long-term conversations.
Memory: gives Agents the ability to store and recall information from previous interactions, allowing them to learn user preferences and personalize their responses.