VoltAgent

Platforms & APIs 💻 TypeScript ⚖️ MIT 🟢 Actively maintained
10.6k stars

VoltAgent is an end-to-end AI Agent Engineering Platform with an open-source TypeScript framework for building agents with memory, tools, workflows, and multi-agent systems, plus a VoltOps Console for observability, automation, and deployment. It solves the problem of moving from prototype to production by providing code control and operational tooling. It is for developers building AI agents and multi-agent workflows.

How To Create AI Agents From Scratch with JavaScript - AI Recipe Generator Example

🎬 How To Create AI Agents From Scratch with JavaScript - AI Recipe Generator Example · VoltAgent

VoltAgent demo
🖼️ Screenshot from the project README

✨ Key features

  • Define agents with typed roles, tools, memory, and model providers.
  • Declarative workflow engine for multi-step automations.
  • Supervisor runtime for teams of specialized sub-agents.
  • Zod-typed tools with lifecycle hooks and MCP support.
  • Swap AI providers (OpenAI, Anthropic, Google) via config.
  • Resumable streaming and durable memory adapters.

🎯 Use cases

  • Build a customer support agent with memory and tools.
  • Create a multi-agent research assistant that generates reports.
  • Automate expense approval with human-in-the-loop workflows.
  • Deploy a WhatsApp chatbot for food orders.
  • Convert YouTube videos to blog posts using MCP tools.

📦 Installation

🧰 Requirements: Requires Node.js and npm; uses an OpenAI API key for the default model in the quick start.

npm create voltagent-app@latest

This command guides you through setup.

🚀 Usage

import { VoltAgent, Agent, Memory } from "@voltagent/core";
import { LibSQLMemoryAdapter } from "@voltagent/libsql";
import { createPinoLogger } from "@voltagent/logger";
import { honoServer } from "@voltagent/server-hono";
import { openai } from "@ai-sdk/openai";
import { weatherTool } from "./tools";

const logger = createPinoLogger({ name: "my-agent-app", level: "info" });
const memory = new Memory({ storage: new LibSQLMemoryAdapter({ url: "file:./.voltagent/memory.db" }) });

const agent = new Agent({
  name: "my-agent",
  instructions: "A helpful assistant that can check weather and help with various tasks",
  model: openai("gpt-4o-mini"),
  tools: [weatherTool],
  memory,
});

new VoltAgent({
  agents: { agent },
  workflows: {},
  server: honoServer(),
  logger,
});

Then run npm run dev.

❓ FAQ

How do I create a new VoltAgent project?

Run npm create voltagent-app@latest and follow the setup prompts.

Can I use different AI providers?

Yes, you can swap between OpenAI, Anthropic, Google, or others by changing the model configuration.

How do I interact with my agent after starting the server?

Open the VoltOps Console link from the terminal, find your agent, and use the chat icon to send messages.

What is the VoltOps Console?

It is the platform side providing observability, automation, deployment, and more for your agents.

📊 Repository

Stars★ 10,552
Forks🍴 1,120
Open issues🐛 82
Last commit🕒 Aug 27, 2026
Created📅 Apr 2025
Language💻 TypeScript
License⚖️ MIT

🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.