Skip to main content

A lightweight, local AI chatbot system with text-to-speech capabilities

Project description

Mythic-Lite

🪄 What is Mythic? (the non-boring version)

Mythic is my playground for weird AI ideas.
Think: Roblox clowns, cursed TikTok experiments, and NPCs with emotional damage.

Yes, it’s half-baked. But half-baked on purpose.
Runs locally, talks back, and might roast you if you let it.

Right now it’s roleplaying as a 19th-century mercenary who talks funny.

🚀 Features

  • Local AI Processing: Run completely offline using local LLM models
  • Text-to-Speech: Natural voice synthesis with customizable voices
  • Speech Recognition: Lightweight offline ASR system using Vosk for voice input
  • Conversation Memory: Intelligent conversation management with automatic summarization
  • Beautiful CLI Interface: Modern, intuitive command-line interface with rich output
  • Modular Architecture: Separate workers for LLM, TTS, ASR, and summarization tasks
  • Rich Logging: Comprehensive logging with configurable output formats
  • Environment Configuration: Flexible configuration via environment variables
  • Automated Setup: One-click environment setup with virtual environment and dependencies

🏗️ Architecture

Mythic-Lite uses a modular architecture with specialized workers:

  • Chatbot Orchestrator: Coordinates all components and manages conversation flow
  • LLM Worker: Handles language model inference and text generation
  • TTS Worker: Manages text-to-speech synthesis
  • ASR Worker: Handles automatic speech recognition for voice input
  • Summarization Worker: Handles conversation summarization for memory management
  • Conversation Worker: Manages conversation state and memory

📋 Requirements

  • Python 3.8+
  • Windows 10/11, Linux (Ubuntu 18.04+), or macOS 10.15+
  • At least 8GB RAM (16GB+ recommended)
  • Sufficient storage for model files (~4-8GB)
  • Audio input/output capabilities

📁 Project Structure

mythic-lite/
├── src/mythic_lite/          # Main package source code
│   ├── core/                 # Core components (orchestrator, config, etc.)
│   ├── workers/              # Specialized AI workers (LLM, TTS, ASR, etc.)
│   ├── utils/                # Utilities (CLI, logging, etc.)
│   └── scripts/              # Setup and utility scripts
├── tests/                    # Test suite
├── docs/                     # Documentation
├── examples/                 # Usage examples
├── scripts/                  # Installation and startup scripts
├── pyproject.toml           # Modern Python packaging configuration
├── requirements.txt          # Runtime dependencies
├── requirements-dev.txt      # Development dependencies
└── README.md                # This file

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

mythic_lite-0.1.0.tar.gz (72.9 kB view details)

Uploaded Source

Built Distribution

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

mythic_lite-0.1.0-py3-none-any.whl (73.5 kB view details)

Uploaded Python 3

File details

Details for the file mythic_lite-0.1.0.tar.gz.

File metadata

  • Download URL: mythic_lite-0.1.0.tar.gz
  • Upload date:
  • Size: 72.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.13

File hashes

Hashes for mythic_lite-0.1.0.tar.gz
Algorithm Hash digest
SHA256 1fea815c63e4e6c1ca4ecc247d2640365864f4ab6dd99723d5174fb66363ba78
MD5 32ec3f8fe3b2966d61ee49d0b9780baa
BLAKE2b-256 afa166602171331380a8562994b72ced997f9c9db7a30323368f836b921e189b

See more details on using hashes here.

File details

Details for the file mythic_lite-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: mythic_lite-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 73.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.13

File hashes

Hashes for mythic_lite-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 20a10dc500e3782864ac7b976875b87f27d12b4aef34475412020489a107442e
MD5 d0775340576be3576a7d73d42b7dff3e
BLAKE2b-256 add9ae78a33d747332e6c1318c8e103d151a156bd6174b3508b6116f554d8f10

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