Source code</>
infinite-livestream
Experimental
infinite-livestream
An end-to-end reference implementation where Twitch or YouTube prompts become expanded scenes, generated clips, and a continuous RTMP broadcast.
Open source / Moderated AI alien TV from YouTube chat
infinite-slop-engine
A one-day open-source experiment that moderates and rewrites YouTube chat before generating short H3 Max clips for a live broadcast.
View repository ↗Source code</>
infinite-slop-engine
The unlock
Why this one is on the map.
It surfaces the safety and latency trade-off in chat-driven AI TV: multi-stage moderation before a prompt reaches the screen.
The project exposes an important constraint of public AI TV: audience input needs moderation and rewriting before it reaches a generative model and a live broadcast.
This is source code, not a hosted channel. You need to inspect, configure, and deploy it with your own keys and runtime before anything can broadcast.
How to read it
What happens when you open it.
Review the repository’s moderation stages and H3 Max clip flow, then run it with the required YouTube and model configuration. It is an experiment rather than a maintained hosted service.
Best for: Builders studying prompt safety, moderation latency, and chat-to-video broadcast pipelines.
Access note: Open source experiment; self-hosting and provider configuration required.
Sources & status
Keep the link, keep the caveat.
One-day experiment from 2026-08-30, supplied as an open-source reference. It is not maintained as a production product.
Explore similar projects
Suggest a correction ↗Source code</>
SlopTV
Experimental
SlopTV
An open-source loop that turns YouTube chat comments into video prompts, renders short clips with a local GPU workflow, and sends them back via RTMP.
Source code</>
UNREEL
Experimental
UNREEL
An open-source, self-hosted AI streaming service that writes scenes and renders MiniMax H3 Max Turbo video through fal as a channel plays.