AAswordman/Operit
Operit
Operit is a private, voice-enabled AI agent designed to run quantized large language models offline within mobile Linux environments. It functions as a plugin-based agent that combines local inference with a hands-free interaction pipeline.
The system distinguishes itself through the use of role cards to manage distinct AI personas and conversation histories. It integrates a voice-driven interface utilizing speech-to-text and text-to-speech modules, and it enables device automation by dispatching shell commands and accessibility services to navigate user interfaces.
The project further covers remote workspace synchronization via standard file transfer protocols and a memory management system that summarizes conversation history. It also provides a framework for connecting external services and custom scripts to the AI agent through standardized tool interfaces.
Features
- Voice Interaction Management - Provides a comprehensive voice interaction system with wake-word detection, speech recognition, and synthesis.
- GGUF Assistants - Provides a private, voice-enabled AI agent utilizing quantized GGUF models for offline mobile execution.
- Conversational Voice AI - Ships a complete hands-free interaction pipeline combining speech-to-text and text-to-speech for natural conversations.
- Persona Configurations - Defines specific AI personalities and speaking styles through the use of role cards.
- Local Model Execution - Runs large language models offline using GGUF formats to ensure data privacy.
- GGUF Execution - Executes quantized large language models offline using the GGUF format for low memory usage.
- Persona Definitions - Uses role cards to maintain distinct conversational identities and isolated history buffers.
- Voice Assistants - Implements a full voice assistant system for hands-free conversational interaction and device control.
- Voice Interaction Loops - Implements a continuous voice loop combining speech-to-text and text-to-speech for hands-free interaction.
- Mobile Device Automation - Automatically navigates user interfaces and performs device tasks via shell commands and accessibility services.
- Shell-Driven UI Automation - Dispatches shell commands to accessibility services to automatically navigate and interact with mobile user interfaces.
- Mobile Linux Shells - Runs shell commands and manages software packages within a full Linux environment on a mobile device.
- LLM Mobile Deployments - Deploys large language models on mobile devices using compact quantized formats.
- AI Personas - Creates specialized AI personalities with distinct behavioral identities via role cards.
- Plugin-Based Agent Integrations - Provides a standardized interface to connect external services and custom scripts as tools for the AI agent.
- AI Agent Plugins - Provides a plugin system that allows the AI agent to interface with external applications and custom scripts.
- Conversation Memory Managers - Manages and summarizes interaction history to maintain context and track user preferences.
- External Tool Integrations - Integrates third-party services and custom workflows for tasks like file manipulation and web requests.
- Context Summarizations - Compresses long-term conversation history into categorized summaries to optimize the model context window.
- AI Agents - AI-powered chat and command execution software.
