TokBrain transforms Douyin public videos into a local, searchable, and traceable multimodal knowledge base with permission-aware processing, AI summarization, and RAG Q&A.

Stars

9

7-day growth

No data

Forks

1

Open issues

0

License

MIT

Last updated

2026-07-28

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It explicitly respects content creators' download permissions, uses a local-first architecture to keep data on the user's machine, and integrates OCR, ASR, keyframe extraction, and AI-powered summarization with grounded Q&A—all while emphasizing compliance and risk awareness for non-official platform access.

Who it is for

  • Personal knowledge managers who want to repurpose information from Douyin public videos
  • Researchers or learners who analyze Douyin content for educational or study purposes
  • Obsidian users who need to export structured notes and media assets from Douyin
  • Privacy-conscious individuals who prefer local data storage over cloud services

Use cases

  • Building a personal knowledge base from tutorial or educational Douyin videos
  • Extracting and summarizing text from video subtitles, speech, and on-screen text via OCR/ASR
  • Querying your knowledge base with natural language questions and getting answers with source references
  • Exporting structured summaries and keyframes to Obsidian for long-term note management

Strengths

  • Permission-aware pipeline: only fully downloads media when the author explicitly allows it; otherwise falls back to subtitles and metadata
  • Fully local storage: SQLite database, extracted assets, and indexes remain on the user's machine, with optional cloud AI processing
  • Multimodal processing: combines keyframe extraction, OCR, ASR, and AI summarization for comprehensive content understanding
  • Grounded RAG: answers are accompanied by source references back to the local summaries and original public links

Considerations

  • Windows-only (depends on Windows DPAPI for key encryption)
  • Requires Alibaba Cloud Bailian API key for OCR, ASR, summarization, and vector embedding—external cloud dependency
  • Designed solely for manual, low-volume personal use (max 10 links per batch, 150 F2 resolves per day); not for bulk or automated scraping
  • Users must accept platform risk (account ban, cookie expiration, IP blocking) and comply with Douyin’s terms of service

README quick start

快速开始

Description

Preserve knowledge, sustain wisdom forever.

Related repositories

Similar projects matched by category, topics, and programming language.

jamesob
Featured
jamesob GitHub avatar

local-llm

A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.

AI & Machine LearningLarge Language Models
1,660
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
react
Featured
react GitHub avatar

react

React is a JavaScript library for building user interfaces with declarative, component-based, and cross-platform design.

Web DevelopmentFrontend Frameworks
246,741