AI app dependency auditor

Finds what your AI app silently downloads, especially offline

Problem

An AI app may look like it just needs an API key, but often silently downloads models, dependencies, binaries and remote assets at install or runtime, tripping up offline deployment, security audits and compliance checks. Developers usually discover this only when shipping to a locked-down environment.

Solution

Statically scan the project and run it in a sandbox, recording every external network call and download, marking what is required vs. prefetchable or replaceable, and producing an actionable report with fixes. Meant to run before packaging, private deployment or compliance review.

Users

AI teams doing private deployments, enterprise developers needing offline/intranet installs, engineering leads focused on supply-chain security

MVP

Scan dependency manifests and install scripts for download sources; run in a container sandbox and capture egress; produce a dependency-origin risk list; suggest one-click prefetch or replacement

Revenue

Open-source core plus team subscription (private rules, CI integration, report archiving); priced per repository

Why now

More AI apps need offline and private deployment while supply-chain security keeps rising; auditing is manual today, leaving room for a focused tool a solo dev can build