๐ Introduction
Hey builders, creators, and AI tinkerers, Iโm Maxime Yao, an 20-year-old Business student at the University of Exeter and a Product Manager intern at Amazon. For the past two months, Iโve been building AceClip.com solo AI-powered system that turns long-form videos (podcasts, interviews, lectures) into short, searchable, personalised knowledge clips. Iโm now looking for a technical co-founder to help take AceClip from a working MVP to a production-ready web platform. If youโre passionate about AI, education, and the future of knowledge discovery, this might resonate with you.
๐ฌ What Is AceClip?
AceClip is your โpersonal YouTube brain.โ It helps users find, organize, and revisit the smartest moments buried inside hours of video content.
Core functions:
- ๐ง Automatically detects the most insightful moments in podcasts & interviews
- โ๏ธ Generates professional short-form clips with captions, face cropping, and speaker tracking
- ๐ Supports semantic video search using RAG + vector embeddings
- ๐ Builds a personalized knowledge library an encyclopedia of ideas tailored to you
Think of it as the next evolution of intentional learning: turning internet noise into structured, actionable wisdom.
โ๏ธ How It Works โ Under the Hood
- Language & video stack: Python | OpenCV | FFmpeg | GPT for semantic understanding
- Perception & audio: InsightFace for facial recognition, pyannote.audio for diarization
- Knowledge layer: RAG + embeddings for search; DeepSeek-OCR for 10ร transcript compression
- Performance: Processes 1 hour of video in โ 15 minutes on cloud GPUs
- Scalability: Embedding billions of minutes for <$100 one-time processing and $10โ20 monthly storage
- Codebase: ~15 K modular lines (AI-assisted); local backend fully automated at MVP stage
The system chunks transcripts into 3โ7 minute segments (โ1 000โ1 500 words), indexes metadata (speakers, timestamps, topics), and enables natural-language queries across millions of clips.
๐ Vision & Roadmap
Phase 1 โ Core AI pipeline โ โ
Complete (MVP) Phase 2 โ Web platform โ Upload videos / YouTube links, generate clips for creators & learners Phase 3 โ Discovery engine โ Scan 300 K + podcasts for niche topics (โhow to grow on LinkedInโ, etc.) and serve as a content repurposing and recommendation system
Weโre targeting the $500 M + content-tech market, where existing tools (Opus.pro, NotebookLM, Perplexity) still struggle with moment accuracy and cost. AceClip aims to win through precision in context detection and low-cost scalability (self-hosted on Vast.ai, Salad, Cloudflare R2). ๐ก Origin Story
Iโve spent 10 000 + hours watching 100 + high-signal YouTube channels (Founders Podcast, Peter Diamandis, My First Million, Superwall HQ, etc.). The problem: wisdom is buried in hours of video hard to find, hard to revisit. AceClip was born from that pain a tool I built for myself that grew into a mission to help everyone learn more intentionally.
๐งฉ Who Iโm Looking For
A technical or design-minded co-founder who:
- Is strong in Python / AI / ML or web development (FastAPI, React preferred)
- Cares about education, productivity, and content tech
- Builds fast, thinks big, and communicates openly
- Is comfortable refactoring and scaling existing MVPs into production systems
Iโm transparent about my own gaps I handle product, vision, and user research, and I need support on architecture, integration, and full-stack deployment. We can start with an NDA + code review to discuss fit and next steps.
๐ Why Join AceClip?
This isnโt just another AI wrapper, itโs a movement toward intentional learning in an age of information overload.
๐ค Letโs Talk
If this resonates, if you see the inevitable future where AI helps us learn faster and remember smarter, Iโd love to connect.
Letโs build the future of learning together.