AI-powered content moderation API for Discord and web apps. Filter toxic and harmful content in real-time with advanced machine learning models.

Hey everyone, Jaiden here. I built Supervisor, an AI content moderation platform with a REST API at its core, catching toxicity, hate speech, spam, and NSFW content without writing a single regex rule. Plug it into whatever you're building. Discord is one integration we offer, but the API works completely standalone. Just shipped 2.0. What's new: New models with more labels, catching stuff the old ones missed Image moderation, so it's not just text anymore Implicit labeling, meaning it catches things that aren't said outright, not just keyword matches I'm a solo dev on this. It runs on my own ML pipeline rather than wrapping someone else's API, so I control accuracy and can add new detection categories whenever needed. Would love feedback, especially if you're building something that needs content moderation, Discord or otherwise. Bugs, feature requests, "why doesn't it catch X" are all welcome, I read everything here.

Set it up on a small Discord server and it caught spam and slurs within seconds, way faster than the bots I tried before. Pricing feels fair for the accuracy, curious to see how it holds up under heavier traffic.

Supervisor

Moderation that reads intent, not just keywords.

Moderation that reads intent, not just keywords.