ManusPrime

# ManusPrime

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
[![Code Style: Black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)

<!-- This HTML comment trick enables image centering in markdown -->
![ManusPrime Logo](assets/manusprime-logo.svg#gh-light-mode-only)
![ManusPrime Logo](assets/manusprime-logo.svg#gh-dark-mode-only)

> A sophisticated multi-model AI agent framework with intelligent task routing, extensible plugin architecture, and advanced resource optimization.

## ✨ Highlights

- **Smart Model Selection** - Automatically routes tasks to the most suitable AI model
- **Multi-Provider Support** - Seamlessly works with OpenAI, Anthropic, Mistral, DeepSeek, and more
- **Modular Plugin System** - Easily extend capabilities with specialized plugins
- **Advanced Memory System** - Vector-based storage for context-aware responses
- **Resource Optimization** - Intelligent caching, batching, and fallback mechanisms
- **Input Validation** - Enhanced security and prompt optimization
- **Budget Controls** - Fine-grained cost management and tracking

## 🚀 Quick Start

```bash
# Clone repository
git clone https://github.com/ageborn-dev/manusprime.git
cd manusprime

# Setup environment
python -m venv venv
source venv/bin/activate  # or venv\Scripts\activate on Windows
pip install -r requirements.txt

# Configure API keys
cp .env.example .env
# Edit .env with your API keys

# Run the server
python server.py
```

Visit `http://localhost:8000` to access the web interface.

## 🧠 Core Architecture

ManusPrime employs a sophisticated multi-model approach that intelligently routes tasks to the optimal AI model:

┌─────────────┐     ┌───────────────┐     ┌────────────────┐     ┌─────────────┐
│ User Input  │────▶│ Task Analysis │────▶│ Model Selection│────▶│ Execution   │