VoltAgent
ActiveDescription
VoltAgent is an end-to-end AI Agent engineering platform combining a TypeScript framework with the VoltOps console for workflow, MCP, memory, and observability.
Key Features
- Core agent runtime - typed roles, tools, memory, and model providers wired in one place
- Declarative workflow engine - multi-step automations described in code, not graph editors
- Supervisor and sub-agent topology - specialized agents coordinated by a supervisor runtime
- Tool registry and MCP - Zod-typed tools with lifecycle hooks plus MCP server integration
- Resumable streaming - clients reconnect to in-flight streams after page refresh
- VoltOps console - observability, evals, prompt management, deployment, and guardrails
Use Cases
💡 Building a multi-agent expense approval system with supervisor routing
💡 Wiring a Zod-typed tool to a model with lifecycle hooks and cancellation
💡 Running RAG agents that retrieve from a knowledge base before answering
💡 Deploying an agent with prompt management, evals, and guardrails from one console
💡 Attaching durable memory so agents remember context across runs
Categories
Quick Start
# Scaffold a new VoltAgent project
npm create voltagent-app@latest
# Then in src/index.ts:
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 { expenseApprovalWorkflow } from "./workflows";
import { weatherTool } from "./tools";
const logger = createPinoLogger({ name: "my-agent-app", level: "info" });
const memory = new Memory({ storage: new LibSQLMemoryAdapter() });
const agent = new Agent({
name: "expense-bot",
model: openai("gpt-4o"),
tools: [weatherTool],
memory,
});
new VoltAgent({ agents: { agent }, workflows: { expenseApprovalWorkflow }, logger, server: honoServer() });