Agent API

The SekuireAgent class is the core interface for interacting with LLMs.

Loading Agents

getAgent()

Load a single agent by name from sekuire.yml:

TypeScript

import { getAgent } from '@sekuire/sdk';

// Load agent by name
const agent = await getAgent('assistant');

// Load with custom config path
const agent = await getAgent('assistant', './config/sekuire.yml');

Python

from sekuire_sdk import get_agent

# Load agent by name
agent = await get_agent('assistant')

# Load with custom config path
agent = await get_agent('assistant', './config/sekuire.yml')

Rust

use sekuire_sdk::get_agent;

// Load agent by name
let agent = get_agent(Some("assistant"), None).await?;

// Load with custom config path
let agent = get_agent(Some("assistant"), Some("./config/sekuire.yml")).await?;

getAgents()

Load all agents from the config:

TypeScript

import { getAgents } from '@sekuire/sdk';

const agents = await getAgents();
const researcher = agents['researcher'];
const coder = agents['coder'];

Python

from sekuire_sdk import get_agents

agents = await get_agents()
researcher = agents['researcher']
coder = agents['coder']

Rust

use sekuire_sdk::get_agents;

let agents = get_agents(None).await?;
let researcher = agents.get("researcher").unwrap();

---

Chat Methods

chat()

Send a message and get a complete response:

TypeScript

const response = await agent.chat('Hello, how are you?');
console.log(response);

// With options
const response = await agent.chat('Explain quantum computing', {
  temperature: 0.5,
  maxTokens: 500,
});

Python

response = await agent.chat('Hello, how are you?')
print(response)

# With options
response = await agent.chat('Explain quantum computing', {
    'temperature': 0.5,
    'max_tokens': 500,
})

Rust

let response = agent.chat("Hello, how are you?", None).await?;
println!("{}", response);

// With options
let mut options = ChatOptions::default();
options.temperature = Some(0.5);
options.max_tokens = Some(500);
let response = agent.chat("Explain quantum computing", Some(options)).await?;

chatStream()

Stream response tokens for real-time output. See Streaming for details.

---

Conversation History

TypeScript

// Get history
const history = agent.getHistory();
console.log(`Messages: ${history.length}`);

// Clear history
agent.clearHistory();

// History format
// [
//   { role: 'user', content: 'Hello' },
//   { role: 'assistant', content: 'Hi there!' },
// ]

Python

# Get history
history = agent.get_history()
print(f"Messages: {len(history)}")

# Clear history
agent.clear_history()

# History format
# [
#   {'role': 'user', 'content': 'Hello'},
#   {'role': 'assistant', 'content': 'Hi there!'},
# ]

Rust

// Get history
let history = agent.get_history();
println!("Messages: {}", history.len());

// Clear history
agent.clear_history();

// History format: Vec<Message>
// Message { role: "user", content: "Hello" }
// Message { role: "assistant", content: "Hi there!" }

---

Agent Metadata

TypeScript

// Get provider info
const provider = agent.getLlmProvider(); // "openai"
const model = agent.getModelName();      // "gpt-4-turbo"
const tools = agent.getTools();          // ["calculator", "web_search"]

Python

# Get provider info
provider = agent.get_llm_provider()  # "openai"
model = agent.get_model_name()       # "gpt-4-turbo"
tools = agent.get_tools()            # ["calculator", "web_search"]

Rust

// Get provider info
let provider = agent.get_llm_provider(); // "openai"
let model = agent.get_model_name();      // "gpt-4-turbo"
let tools = agent.get_tools();           // ["calculator", "web_search"]

---

API Reference

Method	Description
chat(message, options?)	Send message, get response
chatStream(message, options?)	Stream response tokens
getHistory()	Get conversation history
clearHistory()	Clear conversation
getLlmProvider()	Get LLM provider name
getModelName()	Get model name
getTools()	Get registered tool names

Next Steps

• Built-in Tools - Add capabilities
• Streaming - Real-time responses