AI Hackathons AI Apps AI Tech AI Tutorials AI Articles Surge Sponsor

Footer navigation

Unlocking state-of-the-art artificial intelligence and building with the world's talent

LinkedIn
Twitter/X
Instagram
Discord
YouTube
Twitch

Other group brands:

Links

AI Tech
AI Hackathons
AI Tutorials
AI Applications
Surge
AI Articles
Leaderboard
Writers

lablab

About
Brand
Hackathon Guidelines
Terms of Use
Code of Conduct
Privacy Policy

Get in touch

Discord
Sponsor
Cooperation
Contribute
[email protected]

© 2026 NativelyAI Inc. All rights reserved.

3.26.0

AI app: AuditEye | Sovereign Transparency for AMD Developer Hackathon

Home
App Discovery
AuditEye | Sovereign Transparency

AuditEye | Sovereign Transparency

Streamlit

Created by team AuditEye on May 09, 2026

AMD Developer Cloud Qwen3 AMD ROCm

AI Agents & Agentic Workflows (Best Track for Beginners)Qwen

Government and enterprise procurement processes are plagued by inefficiencies, price bloat, and manual auditing bottlenecks. Traditional SaaS auditing tools require uploading sensitive financial data to third-party clouds, creating massive security and privacy risks. AuditEye solves this by providing a 100% sovereign, locally hosted AI auditing system. Powered by Alibaba Qwen 2.5 running on an AMD Instinct™ MI300X compute node, the system uses LangGraph to orchestrate a deterministic audit workflow. It ingests procurement data (CSV, Excel, PDFs), cross-references requested budgets against internal price lists or live market baselines, and flags anomalies. Designed with local government units and corporate modernization in mind, AuditEye allows institutions to process sensitive documents instantly, securely, and with enterprise-grade reasoning. Your data never leaves your hardware, ensuring tax dollars and corporate budgets are spent transparently.

Category tags:

Finance, Ecommerce

Github Presentation Demo

Explore more applications

Toddle AI

Toddle AI is a privacy-first Android app that analyzes toddler walking videos on-device, checks capture quality, measures gait patterns from pose landmarks, and lets parents ask a local AI assistant to explain the result

Toddle AI

Qualcomm Snapdragon

Lantern: Model anything

Lantern turns a smartphone into an AI-powered 3D scanner. Using on-device AI with ExecuTorch, it generates accurate 3D meshes in real time without cloud processing, LiDAR, or external hardware, making 3D scanning fast, private, and accessible.

Lantern

Meta ExecutorchClaude CodeQualcomm Snapdragon

Memory Recall Assistant

A private, on-device memory assistant for cognitive decline. Using ExecuTorch on Snapdragon 8 Elite NPU, it identifies faces, transcribes conversations via Whisper, and generates warm recall cues via Llama 3.2 1B - fully offline, zero cloud.

Synapse Riders

Meta ExecutorchQualcomm SnapdragonWhisperLlama 3.2AI StudioAnthropic ClaudeGithub Copilot

SafeScreen AI

An on-device visual safety layer that helps protect people from explicit, abusive, and manipulated media before they interact with it.

SafeScreen AI

Qualcomm SnapdragonClaude Code

PrivateDoc

PrivateDoc is an offline, on-device visual assistant that uses ML Kit OCR, ExecuTorch, MiniLM, and Llama 3.2 to scan, index, and answer questions about private documents. Its strict RAG pipeline provides source-grounded answers. Powered by SnapDragon.

Edge Faithful

Qualcomm SnapdragonGithub CopilotMeta ExecutorchLlama 3.2

Jairus Gad Meneses

Upcoming AI Hackathons
For Innovators & Creators

Explore more applications

Toddle AI

Toddle AI is a privacy-first Android app that analyzes toddler walking videos on-device, checks capture quality, measures gait patterns from pose landmarks, and lets parents ask a local AI assistant to explain the result

Toddle AI

Qualcomm Snapdragon

Lantern: Model anything

Lantern turns a smartphone into an AI-powered 3D scanner. Using on-device AI with ExecuTorch, it generates accurate 3D meshes in real time without cloud processing, LiDAR, or external hardware, making 3D scanning fast, private, and accessible.

Lantern

Meta ExecutorchClaude CodeQualcomm Snapdragon

Memory Recall Assistant

A private, on-device memory assistant for cognitive decline. Using ExecuTorch on Snapdragon 8 Elite NPU, it identifies faces, transcribes conversations via Whisper, and generates warm recall cues via Llama 3.2 1B - fully offline, zero cloud.

Synapse Riders

Meta ExecutorchQualcomm SnapdragonWhisperLlama 3.2AI StudioAnthropic ClaudeGithub Copilot

SafeScreen AI

An on-device visual safety layer that helps protect people from explicit, abusive, and manipulated media before they interact with it.

SafeScreen AI

Qualcomm SnapdragonClaude Code

PrivateDoc

PrivateDoc is an offline, on-device visual assistant that uses ML Kit OCR, ExecuTorch, MiniLM, and Llama 3.2 to scan, index, and answer questions about private documents. Its strict RAG pipeline provides source-grounded answers. Powered by SnapDragon.

Edge Faithful

Qualcomm SnapdragonGithub CopilotMeta ExecutorchLlama 3.2