Case study
Open sourceTikTok UGC Pipeline
A local Python toolkit that discovers TikTok videos by keyword, downloads them, and extracts 12 evenly-spaced frames per video for creative research.
Facts
- Status
- Open source
FIG. 001 / ARCHITECTURE
How the system connects
Live model
Problem
Sourcing and reviewing TikTok UGC/ad creative for reference or research means manually finding relevant videos, downloading them, and scrubbing through each one to pull representative stills — slow when doing this across many videos at once.
System
Playwright (Firefox) drives keyword-based TikTok discovery using the user's own session token, a downloader pulls full videos by URL, and FFmpeg extracts 12 frames per video for quick visual scanning. An optional Dockerized API console exists as a separate workflow for browsing results. Everything runs on the operator's own machine against their own TikTok access — no third-party server is involved.
FIG. 002 / HOW IT WORKS
How it works
Built to make TikTok creative research repeatable rather than manual: point it at a keyword or a video URL and it handles discovery, download and frame extraction as one local pipeline, with setup guides written for both human users and AI coding agents. It's a public, self-contained tool with no dependency on someone else's hosted service.
Stack
What it runs on
Related systems
UBA-BRAIN
Internal toolA shared markdown knowledge base and rule system that lets any AI CLI on any machine run the same client work with the same rules, memory and skills.
AI Product Visuals Pipeline
Internal toolA skill-driven pipeline that turns a client's chat request into an on-brand AI product photo, picking the right account, model and reference automatically.
TruckPulse
Internal toolAutomated load-profitability and dispatcher-performance monitoring for a trucking company, built from Gmail broker PDFs and Telegram driver-rate messages.
Want a system like this for your team?
We start by mapping one workflow on a 30-minute call.