VoltAgent
An open-source TypeScript AI agent framework under MIT, with multi-agent workflows and a cloud or self-hosted console for tracing and evaluations.
VoltAgent is an MIT-licensed TypeScript AI agent framework for developers building assistants and automated workflows. It pairs code-based agent development with VoltOps, a console for inspecting execution and managing agents. The console can run on your own server or as a cloud service; managed deployment uses hosted infrastructure.
The framework supports agents with memory, access to tools, and retrieval-augmented generation (RAG) for working with knowledge sources. Specialized agents can work under a supervisor that assigns tasks and coordinates their work. Multi-step workflows support human approval, with the ability to pause and resume execution.
Model support includes OpenAI, Anthropic, and Google. Developers can change providers without rewriting the agent logic. MCP connections let agents use external tools, while voice support and guardrails cover spoken interactions and content boundaries. Self-hosting the console is separate from model hosting: these named providers process model requests through their services.
VoltOps exposes execution traces, logs, and performance metrics so developers can investigate what happened during an agent run. It also lets them inspect memory and conversation history, test prompts, and run evaluations of agent behavior and accuracy.
For event-driven automation, workflows can respond to webhooks, schedules, and custom triggers. Slack actions support channel replies, and Airtable actions let agents react to records and write updates back.
