Happy slice of mcp pizzaMCP.pizza

voltagent

MCP.Pizza Chef: VoltAgent

VoltAgent comes in two halves. The open-source framework gives developers memory, retrieval from their own documents, guardrails, voice, multi-step workflows, and supervisors that let several specialist agents share a job, with any MCP server's tools available without extra wiring. The VoltOps console, hosted or run yourself, then shows what each agent did, scores its answers, and manages prompts. You can swap between OpenAI, Anthropic, and Google by changing settings rather than rewriting.

Coding
Data

Use This MCP client To

Build an agent that remembers past conversations Answer questions using my own documents Split a job across several specialist agents Watch a run step by step to see what went wrong Give my agent tools from an MCP server Switch model providers without rewriting my agent Add speech in and speech out to an agent

README


VoltAgent is an open source TypeScript framework for building and orchestrating AI agents.
Escape the limitations of no-code builders and the complexity of starting from scratch.

npm version Contributor Covenant Discord Twitter Follow


What is VoltAgent?

An AI Agent Framework provides the foundational structure and tools needed to build applications powered by autonomous agents. These agents, often driven by Large Language Models (LLMs), can perceive their environment, make decisions, and take actions to achieve specific goals. Building such agents from scratch involves managing complex interactions with LLMs, handling state, connecting to external tools and data, and orchestrating workflows.

VoltAgent Developer Console Demo

VoltAgent is an open-source TypeScript framework that acts as this essential toolkit. It simplifies the development of AI agent applications by providing modular building blocks, standardized patterns, and abstractions. Whether you're creating chatbots, virtual assistants, automated workflows, or complex multi-agent systems, VoltAgent handles the underlying complexity, allowing you to focus on defining your agents' capabilities and logic.

Instead of building everything from scratch, VoltAgent provides ready-made, modular building blocks:

voltagent FAQ

Do I need to write code?
Yes — it is a TypeScript framework, so agents are built in a code project rather than a settings screen.
How do I start?
Create a project with its starter command, add your model key, and run it locally.
Do I need a key?
You supply a key for whichever model you use, such as OpenAI, Anthropic, or Google.
Can I use this to connect an MCP server?
Yes — MCP support is built in, so tools from a server you already run can be handed to your agents.
Can I see what my agents are doing?
Yes — the VoltOps console shows each run, and you can use the hosted version or host it yourself.
Am I locked to one model provider?
No — switching providers is a settings change rather than a rewrite.