> ## Documentation Index > Fetch the complete documentation index at: https://praison.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Agent • Rust AI Agent SDK > Agent: The core Agent struct Agents are the primary execution unit in PraisonAI. They combine: - LLM provider for generating responses - Tools for... # Agent > Defined in the [**agent**](../modules/agent) module. Rust AI Agent SDK The core Agent struct Agents are the primary execution unit in PraisonAI. They combine: - LLM provider for generating responses - Tools for performing actions - Memory for conversation history - Instructions for behavior ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} %%{init: {'theme': 'base', 'themeVariables': { 'primaryColor': '#8B0000', 'primaryTextColor': '#fff', 'primaryBorderColor': '#710101', 'lineColor': '#189AB4', 'secondaryColor': '#189AB4', 'tertiaryColor': '#fff' }}}%% graph LR input["Input Data"] --> agent["Agent: Agent"] agent --> output["Output Result"] style agent fill:#8B0000,color:#fff style input fill:#8B0000,color:#fff style output fill:#8B0000,color:#fff ``` ## Fields | Name | Type | Description | | -------------- | --------------------------------------- | ------------------- | | `id` | `String` | Unique agent ID | | `name` | `String` | Agent name | | `instructions` | `String` | System instructions | | `llm` | `Arc<dyn LlmProvider>` | LLM provider | | `tools` | `Arc<RwLock<ToolRegistry>>` | Tool registry | | `memory` | `Arc<RwLock<Memory>>` | Memory | | `config` | `AgentConfig` | Configuration | ## Methods ### `new` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} fn new() -> AgentBuilder ``` Create a new agent builder ### `simple` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} fn simple(instructions: impl Into) -> Result ``` Create an agent with minimal config **Parameters:** | Name | Type | | -------------- | ------------------------- | | `instructions` | `impl Into<String>` | ### `id` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} fn id(&self) -> &str ``` Get the agent ID ### `name` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} fn name(&self) -> &str ``` Get the agent name ### `instructions` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} fn instructions(&self) -> &str ``` Get the instructions ### `model` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} fn model(&self) -> &str ``` Get the LLM model name ### `chat` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} async fn chat(&self, prompt: &str) -> Result ``` Chat with the agent (main entry point) This is the primary method for interacting with an agent. It handles the full conversation loop including tool calls. **Parameters:** | Name | Type | | -------- | ------ | | `prompt` | `&str` | ### `start` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} async fn start(&self, prompt: &str) -> Result ``` Start a conversation (alias for chat) **Parameters:** | Name | Type | | -------- | ------ | | `prompt` | `&str` | ### `run` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} async fn run(&self, task: &str) -> Result ``` Run a task (alias for chat) **Parameters:** | Name | Type | | ------ | ------ | | `task` | `&str` | ### `add_tool` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} async fn add_tool(&self, tool: impl Tool + 'static) -> () ``` Add a tool to the agent **Parameters:** | Name | Type | | ------ | --------------------- | | `tool` | `impl Tool + 'static` | ### `tool_count` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} async fn tool_count(&self) -> usize ``` Get the number of tools ### `clear_memory` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} async fn clear_memory(&self) -> Result<()> ``` Clear conversation memory ### `history` ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} async fn history(&self) -> Result> ``` Get conversation history ## Source `praisonai/src/agent/mod.rs` at line 39 *** ## Related Documentation