A visual platform for building, testing and deploying AI agents and workflows, with built-in API and MCP server exposure.
VoltAgent/voltagent
TypeScript framework for building AI agents with memory, tools, MCP, RAG, voice and workflows, plus the VoltOps console for observability.
- Stars
- 10,846
- Forks
- 1,419
- Open issues
- 125
- Last commit
- 5 days ago
What is it?
VoltAgent is an AI agent engineering platform with an open-source TypeScript framework at its core. Developers define agents with typed roles, tools, memory and model providers in code, and can switch between providers such as OpenAI, Anthropic and Google through configuration. The framework also covers multi-step workflows, supervisor-coordinated sub-agents, Zod-typed tools, Model Context Protocol server connections, resumable streaming, retrieval-augmented generation, voice input and output, guardrails and evals.
The companion VoltOps Console handles the operational side. It provides execution traces, logs, memory inspection, a prompt builder, deployment, triggers and actions, monitoring, and dashboards for agents running in production. Both cloud and self-hosted options are listed.
The project is distributed as npm packages such as @voltagent/core, and a create-voltagent-app CLI scaffolds a starter project with an example agent and workflow.
Key features
- 01Define agents with typed roles, tools, memory and model providers in TypeScript.
- 02Run supervisor-coordinated teams of sub-agents.
- 03Declarative multi-step workflows with suspend and resume for human approval.
- 04Connect to MCP servers and expose Zod-typed tools with lifecycle hooks.
- 05Built-in RAG, voice (TTS/STT), guardrails and evals.
- 06VoltOps console for traces, logs, memory inspection and deployment.
Use cases
- Building multi-agent systems where specialized agents are coordinated by a supervisor.
- Adding retrieval-grounded answers from your own documents to a chatbot.
- Creating human-in-the-loop automations that pause for manager approval.
- Monitoring and debugging production LLM agents with traces and logs.
Quick start
- 1
Create a new VoltAgent project with the CLI
npm create voltagent-app@latest - 2
Go to the project folder and start the dev server
npm run dev
Things to know
- The VoltOps console used for chatting and observability is a separate cloud or self-hosted service.
- The starter example uses OpenAI, so you need an OpenAI API key to run the agent.
Topics
FAQ
- What is voltagent?
- TypeScript framework for building AI agents with memory, tools, MCP, RAG, voice and workflows, plus the VoltOps console for observability. VoltAgent is an AI agent engineering platform with an open-source TypeScript framework at its core. Developers define agents with typed roles, tools, memory and model providers in code, and can switch between providers such as OpenAI, Anthropic and Google through configuration. The framework also covers multi-step workflows, supervisor-coordinated sub-agents, Zod-typed tools, Model Context Protocol server connections, resumable streaming, retrieval-augmented generation, voice input and output, guardrails and evals.
- Is voltagent free to use? What license does it have?
- voltagent is open source under the MIT license. Check the license terms before using it in commercial products.
- Is voltagent still maintained?
- Actively maintained. The last commit to voltagent was on Oct 15, 2026.
- What can I use voltagent for?
- Building multi-agent systems where specialized agents are coordinated by a supervisor. Adding retrieval-grounded answers from your own documents to a chatbot. Creating human-in-the-loop automations that pause for manager approval. Monitoring and debugging production LLM agents with traces and logs.
- How do I install voltagent?
- Create a new VoltAgent project with the CLI: npm create voltagent-app@latest Go to the project folder and start the dev server: npm run dev
- Where can I get voltagent?
- The source code and installation instructions are on GitHub: https://github.com/VoltAgent/voltagent
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
An open source MCP server that connects AI agents, IDEs and apps to databases with prebuilt tools or custom tool definitions.
Python framework for building autonomous AI agents that research, plan, code and run tasks, with memory, RAG and 100+ LLM providers.
Open-source SDK for building and running AI agents in Python and TypeScript, with tools, MCP, memory, and model portability.
A TypeScript SDK for building persistent, stateful AI agents on Cloudflare Durable Objects, with real-time state sync, scheduling, and MCP support.
A TypeScript framework for building AI agents and LLM-powered applications, with workflows, tools, memory, MCP servers, and evals.