Skip to content

Experiment

Magent: a no-code platform for voice and text agents

Magent is a no-code platform for creating, customising and deploying voice and text agents for customer support, workflow automation and personal assistance. Agents answer from their own knowledge base, search the web, and listen and speak.

Built in the labLast reviewed 1 min read

Mai has built this in his own research.

Agent platform

  • Node.js
  • Express
  • React
  • TypeScript
  • Vite
  • Supabase
  • pgvector
  • Brave Search
  • Gladia
  • ElevenLabs
On this page

In plain English

Magent is a no-code platform for creating, customising and deploying voice and text agents. It is aimed at three jobs: customer support, workflow automation and personal assistance.

How it works

Agents answer from their own knowledge base, search the web, and listen and speak through speech-to-text and text-to-speech. It is built with Node.js, Express, React, TypeScript and Vite, with Supabase and pgvector for storage, Brave Search for the web, and Gladia and ElevenLabs for voice. The code is on GitHub.

Questions and answers

What is Magent?

Magent is a no-code platform, built by Mai as research, for creating, customising and deploying voice and text agents for customer support, workflow automation and personal assistance.

Where do Magent agents get their answers from?

Each agent answers from its own knowledge base and can also search the web.

Can Magent agents talk as well as type?

Yes. Agents listen and speak through speech-to-text and text-to-speech, so the same agent can work by voice or by text.

Sources

  1. Magent on GitHub (ennersmai/ansatag)github.com