Concepts › I.

Agents

Reference: Agents

An agent is a language model (LLM) which is configured with:

Instructions — the system prompt that tells the model who it is and how it should respond.
Model — which LLM to call, plus any optional model tuning parameters.
Tools — a list of functions or APIs the LLM can invoke to accomplish a task.

Creating an agent


import { Agent } from "kernl";
import { anthropic } from "@kernl-sdk/ai/anthropic";
 
const agent = new Agent({
  id: "jarvis",
  name: "Jarvis",
  model: anthropic("claude-sonnet-4-5"),
  instructions: "You are a helpful assistant.",
});


import { Kernl } from "kernl";
 
const kernl = new Kernl();
kernl.register(agent);

Basic configuration

Option	Description
`id`	Unique identifier (required)
`name`	Display name
`model`	LLM to use
`instructions`	System prompt — can be a string or function
`toolkits`	Array of toolkits
`memory`	Memory settings (`{ enabled: true }`)

Running

Blocking — wait for the full response:


const result = await agent.run("What's 2 + 2?");
console.log(result.response);

Streaming — receive events as they happen:


const stream = agent.stream("Tell me a story");
 
for await (const event of stream) {
  if (event.kind === "text-delta") {
    process.stdout.write(event.text);
  }
}

Dynamic instructions

Instructions can be a function that receives context:


import { Agent } from "kernl";
import { anthropic } from "@kernl-sdk/ai/anthropic";
 
const agent = new Agent<UserContext>({
  id: "assistant",
  name: "Assistant",
  model: anthropic("claude-sonnet-4-5"),
  instructions: (ctx) => `
    You are helping ${ctx.context.user.name}.
    Today is ${new Date().toDateString()}.
  `,
});
 
await agent.run("Hello", {
  context: {
    username: "Tony"
  }
});

Adding tools


import { Agent } from "kernl";
import { anthropic } from "@kernl-sdk/ai/anthropic";
import { math } from "@/toolkits/math";
import { github } from "@/toolkits/github";
 
const jarvis = new Agent({
  id: "jarvis",
  name: "Jarvis",
  model: anthropic("claude-sonnet-4-5"),
  instructions: "You are a helpful assistant with access to tools.",
  toolkits: [math, github],
});

Enabling memory


import { Agent } from "kernl";
import { anthropic } from "@kernl-sdk/ai/anthropic";
 
const jarvis = new Agent({
  id: "jarvis",
  name: "Jarvis",
  model: anthropic("claude-sonnet-4-5"),
  instructions: "You are a helpful assistant. Remember user preferences.",
  memory: { enabled: true },
});

See Memory for details.