Skip to main content
Agents are AI programs where a language model controls the flow of execution. The core of an Agent is a model (LLM) with access to tools, guided by instructions:
  • Model: the LLM controlling the flow of execution. It decides when to reason, use tools or respond.
  • Instructions: prompts guiding the model on how to use tools and respond.
  • Tools: enable Agents to take actions and interact with external systems.
With Agno, you can also equip your Agents with memory, knowledge, storage and the ability to reason:
  • Memory: gives Agents the ability to store and recall information from previous interactions, allowing them to learn and improve their responses.
  • Storage: enables Agents to save session history and state in a database. Model APIs are stateless and storage makes Agents stateful, enabling multi-turn conversations.
  • Knowledge: information the Agent can search at runtime to provide better responses. Knowledge is stored in a vector db and this search at runtime pattern is known as Agentic RAG or Agentic Search.
  • Reasoning: enables Agents to “think” before responding and “analyze” the results of their actions before responding, this improves reliability and quality of responses.
If this is your first time using Agno, you can start here before diving into advanced concepts.

Guides

Learn how to build, run and debug your Agents with the following guides.

Beyond Individual Agents

Agno provides two additional core abstractions for building more complex AI systems:
  • Team: a collection of Agents (or sub-teams) that work together. Each team member can have different expertise, tools and instructions, allowing for specialized problem-solving approaches.
  • Workflow: a deterministic agentic flow defined as a series of steps. Workflows provide structured automation with predictable execution patterns, making them ideal for production systems that require reliable, repeatable processes.

Developer Resources