DEV Community

Mai1100
Mai1100

Posted on

Project Draft: Magent - The Customizable AI Agent Platform

  1. Project Overview
    Vision: Build a user-friendly, subscription-based platform where anyone can create, customize, and deploy AI agents ("Magents") for tasks like customer support, workflow automation, and personal assistance.
    USP:(unique selling point); Combines DeepSeek-R1’s reasoning with Google Titans’ memory for long-term context, wrapped in a no-code/low-code interface.

  2. Core Components
    Feature Tech Details
    Multimodal Interaction React (Frontend) + Gladia/11Labs Voice (STT/TTS) + Text chat with dynamic buttons.
    Knowledge Base Supabase RAG + Brave Search User-uploaded files (PDF, etc.) + 10 scraped websites.
    Agent Workflows DeepSeek-R1 (Reasoning) + V3 (NLP) Appointment booking, CRM updates, task automation.
    Tool Integrations Twilio, Resend, Google APIs WhatsApp, email, Sheets/Calendar, CRM.
    Security OAuth2.0 + RLS User isolation, sandboxed tool execution.

  3. Tech Stack (Finalized)
    Backend: Node.js (Express) + Supabase (PostgreSQL + pgvector).

Frontend: React + TypeScript + shadcn/ui.

APIs:

AI: DeepSeek-V3 (NLP), R1 (Reasoning), Titans (Memory).

Tools: Brave Search, Resend (Email), Twilio (WhatsApp/Calls), Nango (Google Auth).

STT/TTS: Gladia (speech-to-text) + ElevenLabs (text-to-speech).

  1. User Workflow Example User Uploads: PDF → Supabase → chunked/embedded via V3.

Query: “Book a meeting on the 29th” → R1 detects intent → Google Calendar API.

Response: “Booked! Your link: [calendar.event]” + buttons [Modify, Cancel].

API Trace View

How I Cut 22.3 Seconds Off an API Call with Sentry 👀

Struggling with slow API calls? Dan Mindru walks through how he used Sentry's new Trace View feature to shave off 22.3 seconds from an API call.

Get a practical walkthrough of how to identify bottlenecks, split tasks into multiple parallel tasks, identify slow AI model calls, and more.

Read more →

Top comments (0)

A Workflow Copilot. Tailored to You.

Pieces.app image

Our desktop app, with its intelligent copilot, streamlines coding by generating snippets, extracting code from screenshots, and accelerating problem-solving.

Read the docs

👋 Kindness is contagious

Explore a sea of insights with this enlightening post, highly esteemed within the nurturing DEV Community. Coders of all stripes are invited to participate and contribute to our shared knowledge.

Expressing gratitude with a simple "thank you" can make a big impact. Leave your thanks in the comments!

On DEV, exchanging ideas smooths our way and strengthens our community bonds. Found this useful? A quick note of thanks to the author can mean a lot.

Okay