NeuroFilterAI
AI makes YouTube serve your goals, Distraction FREE Youtube.
Details
- Categories
- AIEducation & Learning
- Use Cases
- Time ManagementSkill Building
- Target Audience
- StudentsResearchers
- Pricing
- Freemium from $2.49
- Platforms
- Web
About NeuroFilterAI
YouTube is the best learning resource on the internet. The problem isn't YouTube. It's that YouTube's recommendation algorithm optimizes for watch time, which is directly opposed to why most people open it to study. NeuroFilter takes a different approach: semantic intent filtering. You state a learning objective — "organic chemistry" or "calculus" or "system design" — and the extension embeds that intent using a local transformer model (Xenova/all-MiniLM-L6-v2 via transformers.js). Every YouTube recommendation gets scored by cosine similarity against that intent. Below-threshold videos get blurred in the DOM. Above-threshold videos stay visible. The key property: the filtering is semantically aware. A video titled "JEE Chemistry | SN2 Reactions" scores high for organic chemistry intent. "Top 10 Gaming Moments 2024" scores near zero. Keyword blockers can't make that distinction — they don't know what you're there to learn. Built for students, developers, researchers, and anyone who uses YouTube intentionally. Technical: MV3 Chrome extension, WASM inference in offscreen document (avoids service worker lifecycle issues), LRU cache for repeat recommendations, ~3s cold start, then near-instant. Solo-built by Piyush, 17, Gorakhpur — during recovery from Ankylosing Spondylitis.
Product Insights
NeuroFilterAI utilizes semantic intent filtering via on-device transformer models to align YouTube recommendations with specific learning objectives. This freemium web extension enables intentional studying by blurring distractions based on cosine similarity scores rather than simple keywords.
- Privacy-focused on-device inference using WASM and local transformer models.
- Semantically aware filtering that distinguishes between educational content and entertainment.
- Near-instant performance using an LRU cache for processing repeat recommendations.
- Manifest V3 compliant architecture using an offscreen document for stable execution.
Ideal for: Students and researchers can use this tool to maintain focus on YouTube by filtering recommendations to match their specific academic or professional learning goals.
Discount Codes
"3 Month Free + Additional Discounts"(-100% OFF)
Valid until Jun 30, 2026
Product Video
Watch a video demo of NeuroFilterAI.
Screenshots
Product Updates (1)
welcome automation just shipped
I'm Piyush, The extension uses on-device transformers (MiniLM-L6-v2 via WASM and Gemini) to semantically score YouTube recommendations against your stated learning intent. No server. No privacy concerns. The whole inference pipeline runs inside an offscreen document inside the Chrome extension. Current state: - 14 CWS users - v4.5 shipped May 8 - Welcome email automation just deployed: every new signup gets a unique 30-day Pro key minted in Supabase and emailed automatically via Resend. Zero manual action, no VPS, no cron jobs. Honest limitations: - ~3 second cold start (WASM init + model load) - Firefox not yet supported - Using a general-purpose embedding model (not fine-tuned on educational content) If you use YouTube to study or research anything — this is for you. Happy to dig into the technical architecture in the comments.
Comments (0)
No comments yet. Be the first to share your thoughts!
Reviews (0)
peerpush is actually helping me a lot!!! most affordable value for money DR 73 backlink
Comments (2)
Intressting…
@simonkjellner thank you
Built this solo at 17. On-device transformers in MV3 — no server, no privacy risk. ~3s cold start (WASM init), then near-instant. Happy to go deep on the offscreen document architecture in replies.