Get Started with Funolio

Give your AI agents persistent memory in 5 minutes. Funolio stores, searches, and retrieves your AI conversations so your agents never forget.

📖 API Docs⭐ GitHub
Create AccountAdd API KeyCreate a ProjectTry a ChatInstall Agent

👤 Create Account

Get started by creating your Funolio account:

  1. Visit funolio.com
  2. Click "Sign Up" or "Get Started"
  3. Sign in with Google, GitHub, or email
  4. Choose a username for your bot
💡 Tip: Your username becomes your bot's identity. Choose something meaningful like my-dev-agent or your project name.

Quickstart by LLM Provider

⬡OpenAI Setup
import OpenAI from 'openai';
import { Funolio } from '@funolio/sdk';

const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
const brain = new Funolio({ apiKey: process.env.FUNOLIO_API_KEY });

// After each chat completion, save to Funolio
const completion = await openai.chat.completions.create({
  model: 'gpt-4',
  messages: [{ role: 'user', content: 'Hello!' }],
});

await brain.conversations.create({
  title: 'OpenAI Chat',
  source: 'openai',
  messages: [
    { role: 'user', content: 'Hello!' },
    { role: 'assistant', content: completion.choices[0].message.content },
  ],
});

// Use Funolio context for RAG
const ctx = await brain.context.get({
  message: 'user question here',
  maxTokens: 500,
});
// Prepend ctx.context to your system prompt

🔍 Semantic Search

Search across all your AI conversations with natural language. Powered by embeddings.

🧠 Memory & Facts

Auto-extract facts, decisions, and entities. Your agent remembers everything.

⚡ RAG Context

Get relevant context for any message. Perfect for retrieval-augmented generation.

📡 Real-time MQTT

Stream conversations in real-time via MQTT. Perfect for agent-mode integration.

👥 Teams

Share conversations and memory across team members and multiple bots.

🔌 Integrations

Slack, browser extension, CLI, GitHub — connect Funolio to your workflow.

Need help? Check out the API docs or open an issue.