Mandor, a versatile and intelligent Multipurpose AI Agent, designed to streamline and revolutionize the way users perform tasks across various domains. Mandor combines cutting-edge technology and seamless orchestration tools to empower users with unparalleled efficiency and productivity.

Powered by Top LLMs

GPT-4o

OpenAI's flagship model with native multimodal support. GPT-4o combines high performance with lower latency and cost, making it suitable for advanced real-time use cases like voice assistants, code generation, and image understanding.

Gemini 2.5 Pro

Created by Google DeepMind, Gemini 2.5 is a versatile AI model trained for both text and code generation. It excels in reasoning tasks, works across Google tools, and supports multimodal queries including image understanding.

Claude 3.7 Sonnet

Developed by Anthropic, Claude 3.7 Sonnet is known for its deep contextual understanding, safety, and aligned responses. It’s great for tasks requiring critical thinking, document analysis, and conversation with a human-like tone.

Advanced Tool Orchestration

Similar to Microsoft Copilot, enabling seamless interaction and integration

Supported Platforms

Windows

Linux

Mac

Screenshots

MCP Integration:

Supports third-party service integrations for enhanced functionality.
Search Engine Integration:

Utilize Google/Bing/Perplexity to find images, articles, files, and the latest information.
App Development:

Build small applications in .NET, Go, Rust, NodeJS, Python, and Powershell for web, desktop, and console.
Messaging Capabilities:

Send messages via WhatsApp, Email, SMS, and more.
File Manager:

Interact with the file system to write files, organize folders, create Word, PDF, PPT, Excel, and text files, and perform coding tasks.
Home Automation:

Seamless integration with hardware devices via MQTT protocol.
Image Creation:

Generate both realistic and illustrative images.
Image Editing:

Apply effects like grayscale, sepia, and blur to modify images.
Image Analysis & Description:

Analyze and describe image contents effectively.
Image Variations:

Create multiple versions of an image.
Mathematical Calculations:

Perform complex mathematical computations.
Music & Melody Creation:

Compose music and melodies.
Presentation Builder:

Create simple PowerPoint presentations or PDFs.
Reminders:

Set up and manage reminders.
Text-to-Audio Conversion:

Read text files aloud in audio format.
Group Management:

Create groups and manage members in WhatsApp
Web Interaction:

Read webpages, create simple websites, and download files.
Data Analysis:

Analyze CSV, PDF, and Excel files, providing predictions and recommendations
YouTube Transcription:

Extract YouTube transcripts for summaries, translations, and essential insights.
CCTV Monitoring:

Analyze MJpeg CCTV footage (e.g., Jagorawi toll road, office cameras).
Custom Personas:

Switch between personalized agent personas.
Conversation Logging & Analysis:

Features coming soon!
File Sharing:

Share locations, files, folders, images, and contacts seamlessly.
Document Creation:

Craft articles, letters, and convert them into Word/PDF files.
Document Summarization:

Analyze, summarize, and translate documents or articles from specific webpages.
Bot Interactions:

Build bots that converse on specific topics.
Visio Files:

Create simple flow charts and diagrams.
File Attachments:

Read image, PDF, Word, Excel, CSV, and text file attachments.
IoT Integration:

Manage PCs/devices via action models.
QR Code Generation:

Create personalized QR codes.
QnA Chat:

Reference text/PDF for dynamic question-answer sessions.
Dynamic Bot Creation:

Customize personas with single or multi-agent modes.