Autonomous Executive General Intelligence System
A.E.G.I.S. is an experimental agentic framework designed to bridge the gap between LLMs and functional personal assistants (like Jarvis). It is not just a chat interface; it is a state-aware system capable of visual perception, decision-making, and tool orchestration.
Powered by LangGraph, this project moves away from linear chains and towards cyclical, graph-based reasoning. The ultimate goal is to create a Domestic Intelligence Hub—a system that can debug your code and manage your smart home environment seamlessly.
- 🌐 Graph-Based Orchestration: Utilizing LangGraph to manage agent state, allowing for loops, retries, and conditional logic.
- 🏠 Smart Home Nexus: Designed to integrate with home automation APIs (e.g., Home Assistant, Philips Hue) to control the physical environment.
- 👁️ Visual Cortex: Integrated multimodal capabilities (GPT-4o / Claude 3.5 Sonnet) to analyze real-time video feeds or uploaded snapshots.
- 🖥️ Command Center UI: A futuristic, functional dashboard built with Streamlit to visualize the agent's "thought process" and outputs.
- 🛠️ Extensible Tooling: A modular design allowing the agent to connect to local files, web search, and system APIs.