Skip to main content

​
Agent

Defined in the 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

​
Fields

NameTypeDescription
idStringUnique agent ID
nameStringAgent name
instructionsStringSystem instructions
llmArc<dyn LlmProvider>LLM provider
toolsArc<RwLock<ToolRegistry>>Tool registry
memoryArc<RwLock<Memory>>Memory
configAgentConfigConfiguration

​
Methods

​
new

fn new() -> AgentBuilder
Create a new agent builder

​
simple

fn simple(instructions: impl Into<String>) -> Result<Self>
Create an agent with minimal config Parameters:
NameType
instructionsimpl Into&lt;String&gt;

​
id

fn id(&self) -> &str
Get the agent ID

​
name

fn name(&self) -> &str
Get the agent name

​
instructions

fn instructions(&self) -> &str
Get the instructions

​
model

fn model(&self) -> &str
Get the LLM model name

​
chat

async fn chat(&self, prompt: &str) -> Result<String>
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:
NameType
prompt&str

​
start

async fn start(&self, prompt: &str) -> Result<String>
Start a conversation (alias for chat) Parameters:
NameType
prompt&str

​
run

async fn run(&self, task: &str) -> Result<String>
Run a task (alias for chat) Parameters:
NameType
task&str

​
add_tool

async fn add_tool(&self, tool: impl Tool + 'static) -> ()
Add a tool to the agent Parameters:
NameType
toolimpl Tool + 'static

​
tool_count

async fn tool_count(&self) -> usize
Get the number of tools

​
clear_memory

async fn clear_memory(&self) -> Result<()>
Clear conversation memory

​
history

async fn history(&self) -> Result<Vec<Message>>
Get conversation history

Rust Overview

Rust Quickstart

Rust Agent Guide

Rust Installation