1. Create your account

Visit the Scoopika platform and create a free account.

2. Create your first agent

Creating a new agent is a breeze. Simply provide a name, optional description, avatar, and a system prompt to guide its behavior. You can even generate agent avatars using AI directly from the platform.

  • Name: The name of the agent. agents are aware of their own names and their companions names.
  • Description: Briefly describe the agent. notice that this is not the agent’s prompt, and only useful when using companions.
  • Avatar: The agent’s avatar. only useful to display it.
  • LLM: The large language model that powers the agent (its brain).
  • Prompt: A set of instructions that the agent will act and behave based on.
  • Voice: Select your agent’s voice. it will be used in voice-based interaction (we provide 2 voices options for now).

3. Manage & Test your agent

After creating an AI agent, You’ll be redirected to its page, where you can manage everything related to it from settings, to tools, and companions. you’ll find links to the documentation in each tab so you never get lost.

Now you can test your agent in the playground. The playground provides both text-based and voice-based interfaces for testing your agent, both of them were built with Scoopika itself (using the React library).

Notice that you need to provide an API key for the LLM provider the agent uses, You’ll see an interface guiding you through what to do, just pay attention that if you choose (add to my account) you won’t need to pass the key again from your code.

4. Setup your app

For React or NextJS applications, refer to this guide.

Generate token

Generate a Scoopika access token, you can click on the settings icon in the platform, give your token a label, copy it and add it to your env file as SCOOPIKA_TOKEN.


Now let’s install Scoopika in your project (server-side environment):

npm install @scoopika/scoopika


Now it’s time to initialize Scoopika in your project:

import { Scoopika } from "@scoopika/scoopika";

const scoopika = new Scoopika({
  keys: {
    openai: "OPENAI_KEY" // just example

Replace the keys with the name-key of the LLMs providers you’re using, see this page to see an example. again if you added the API key to your account you don’t need to pass it again from the code.

See all properties the Scoopika class accepts here.

Run agents in your app

Now you can start running agent in your application (server-side):

import { Scoopika, Agent } from "@scoopika/scoopika";

const scoopika = new Scoopika({...});
const agent = new Agent("AGENT_ID", scoopika);

const response = await agent.run({
	inputs: {
		message: "Hello!"


Web usage

Now you have an agent running on the server-side, but you’re here for web usage, which involves running agents on the client-side too, for that matter keep going to the next page.