DISCLAIMER: This tool is a proof-of-concept designed strictly for educational purposes and data location assistance. It is not a substitute for manual data verification or forensic conclusions. All outputs must be verified against the original evidence.
This project explores the mechanics of AI agents within a forensic context. Its primary utility is to assist in locating evidence within LEAPP reports.
The system utilizes a RAG (Retrieval-Augmented Generation) architecture combined with a custom ReAct (Reasoning + Acting) Agent to parse and interact with report data.
All data processing, vector storage, and report viewing is fully local.
The only external data transmission is strictly for LLM reasoning. This is handled via Open Router using a "Bring Your Own Key" (BYOK) model, ensuring the user retains control over the API connection.
- AI Assistance: A ReAct agent for querying report data.
- Report Viewer: An embedded viewer for browsing the default HTML reports generated by aLEAPP and iLEAPP.
- KML Viewer: A map interface using Leaflet.js to visualize .kml location data.
- Frontend: Electron (HTML, CSS, JavaScript)
- Backend: Python FastAPI