Skip to main content

A framework for building and managing AI agents with memory systems and API endpoints

Project description

Muvius Framework

Muvius Framework Logo

A G E N T - T O - A G E N T
I N T E L L I G E N C E

by MUVIO AI

What is Muvius?

Muvius is a powerful framework for building and managing AI agents with advanced memory systems and seamless inter-agent communication. It provides a structured approach to creating intelligent agents that can:

  • Maintain context through multiple memory systems
  • Communicate with other agents using standardized protocols
  • Handle complex tasks through role-based interactions
  • Scale from simple to complex multi-agent systems

Key Features

1. Memory Systems

  • Episodic Memory: Tracks conversation history and interactions
  • Procedural Memory: Stores agent roles, rules, and procedures
  • Vector Store: Enables semantic search and context understanding

2. Agent Communication

  • Standardized message protocols
  • Dynamic message routing
  • Inter-agent collaboration support

3. Easy Integration

  • FastAPI-based REST endpoints
  • Docker support for easy deployment
  • CLI tools for quick setup and management

Architecture

┌─────────────────────────────────────────────────────────┐
│                     Muvius Framework                    │
├─────────────────────────────────────────────────────────┤
│                                                         │
│  ┌─────────────┐    ┌─────────────┐    ┌─────────────┐  │
│  │ Orchestrator│    │   Agents    │    │   Shared    │  │
│  │             │    │             │    │ Services    │  │
│  └──────┬──────┘    └──────┬──────┘    └──────┬──────┘  │
│         │                  │                  │         │
│  ┌──────▼──────┐    ┌──────▼──────┐    ┌──────▼──────┐  │
│  │  Message    │    │  Memory     │    │  Utilities  │  │
│  │  Routing    │    │  Systems    │    │  & Tools    │  │
│  └─────────────┘    └─────────────┘    └─────────────┘  │
│                                                         │
└─────────────────────────────────────────────────────────┘

Quick Start

1. Installation

# Create and activate virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: .\venv\Scripts\activate

# Install Muvius
pip install muvius

2. Initialize Your Project

# Create a new Muvius project
muvius init

# Create your first agent
muvius create-agent my-agent

3. Start Development

# Start the orchestrator
python -m muvius.orchestrator.main

# Start your agent (in a new terminal)
python -m muvius.agents.my-agent.main

Project Structure

muvius/
├── agents/              # Agent modules
│   └── my-agent/       # Your custom agent
│       ├── memory/     # Memory systems
│       ├── main.py     # Agent logic
│       └── routes.py   # API endpoints
├── orchestrator/       # Message routing
└── shared/            # Common utilities

CLI Commands

# Initialize framework
muvius init

# Create new agent
muvius create-agent <agent-name>

# Delete agent
muvius delete-agent <agent-name>

Memory Systems

Episodic Memory

  • SQLite-based conversation history
  • Automatic message logging
  • Context retrieval for conversations

Procedural Memory

  • YAML-based configuration
  • Role and policy definitions
  • Procedure storage and retrieval

Vector Store

  • Semantic search capabilities
  • Context understanding
  • Long-term memory storage

API Endpoints

Orchestrator

  • POST /process-message: Route messages to agents
  • GET /ping: Health check

Agents

  • POST /interact: Handle agent interactions
  • GET /ping: Health check

Development

Prerequisites

  • Python 3.8+
  • pip
  • virtualenv

Environment Setup

  1. Create .env file:
OPENAI_API_KEY=your_api_key_here

Running Tests

pytest

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Commit your changes
  4. Push to the branch
  5. Create a Pull Request

License

MIT License

Support

For support, please:

  1. Check the documentation
  2. Open an issue on GitHub
  3. Contact the Muvio AI team

Built with ❤️ by Muvio AI

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

muvius-0.2.1.tar.gz (15.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

muvius-0.2.1-py3-none-any.whl (14.5 kB view details)

Uploaded Python 3

File details

Details for the file muvius-0.2.1.tar.gz.

File metadata

  • Download URL: muvius-0.2.1.tar.gz
  • Upload date:
  • Size: 15.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.12

File hashes

Hashes for muvius-0.2.1.tar.gz
Algorithm Hash digest
SHA256 cea9592fad9d900bb5ebac17a207124859f6400a70c9f11faa8bd7e9495968e7
MD5 dc603e069758475366f4344bed33de19
BLAKE2b-256 5e4e32f13e2b4248654b9bfa8886864ae0f659e0e7921bd2021ffc644c77afb0

See more details on using hashes here.

File details

Details for the file muvius-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: muvius-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 14.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.12

File hashes

Hashes for muvius-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ebd25746c94e7b0926d0769a787eb3b954598e7c9a916c099d3ca7c4cf5b6904
MD5 efffc2fdf613335259603338c7606ac9
BLAKE2b-256 7814789af75ff3ac3e739ce27e694a97a91bc66541408f05f52ac3409844d442

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page