Open CLAW Knowledge Distiller ๐ฆ๐
้พ่พ็ฅ่ฏ่ธ้ฆๅจ ยท ้พ่ฆ็ฅ่ญ่ธ้คพๅจ
English ยท ็น้ซไธญๆ ยท ็ฎไฝไธญๆ
Turn YouTube, Bilibili, and Facebook videos into structured knowledge articles in seconds โ locally, for free. ็ง้ๅฐ YouTubeใBilibiliใFacebook ่ง้ข่ฝฌๅไธบ็ปๆๅ็ฅ่ฏๆ็ซ โ ๆฌๅฐ่ฟ่ก๏ผๅฎๅ จๅ ่ดนใ
English
What is Open CLAW Knowledge Distiller?
Open CLAW Knowledge Distiller๏ผ้พ่ฆ็ฅ่ญ่ธ้คพๅจ๏ผkd๏ผis an open-source CLI tool and MCP server built for the Open CLAW AI agent ecosystem. It converts YouTube, Bilibili, and Facebook videos into structured knowledge articles โ automatically, locally, and for free.
How it works:
- If the video has subtitles โ extracts them directly (no transcription needed, faster)
- If no subtitles โ downloads audio and transcribes locally with Qwen3-ASR MLX on Apple Silicon (no API key, no cloud cost)
- Optionally generates a multi-layer AI summary: one-sentence essence + key points + cleaned transcript
Who is it for?
- Researchers and students who need to digest hours of video content quickly
- AI agent users (Claude Code / Open CLAW ้พ่ฆ) who want to process videos programmatically
- Anyone who wants structured notes from videos without watching them in full
Features
| Feature | Details |
|---|---|
| ๐๏ธ Local ASR | Qwen3-ASR MLX runs entirely on-device (Apple Silicon). No API key, no cloud, free forever. |
| ๐ Smart subtitle detection | Auto-detects existing subtitles โ skips ASR for faster processing |
| ๐ค AI summarization | Supports Google Gemini, OpenAI, and Anthropic as summary providers |
| ๐จ 8 summary styles | Standard, Academic, Action List, News Brief, Investment Analysis, Podcast Digest, ELI5, Bullet Notes |
| ๐ MCP Server | Connect from Claude Code, Open CLAW, or any MCP-compatible AI agent |
| ๐ Multilingual | Cantonese (็ฒต่ช), Mandarin, English, Japanese, Korean, and 50+ languages |
| โก Zero API key mode | --no-summary: pure local transcription, no external services needed |
Installation
Prerequisites:
brew install ffmpeg # audio extraction
Install:
pip install openclaw-knowledge-distiller
# or with uv:
uv add openclaw-knowledge-distiller
Qwen3-ASR model (~1-2 GB) downloads automatically from Hugging Face on first use.
Install from source (for development):
git clone https://github.com/destinyfrancis/openclaw-knowledge-distiller.git
cd openclaw-knowledge-distiller
uv sync
Quick Start
# โโ No API key needed (100% local) โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
kd process "https://youtube.com/watch?v=dQw4w9WgXcQ" --no-summary
# Cantonese video with dialect hint
kd process "https://youtube.com/watch?v=..." \
--language yue \
--asr-prompt "้ๆฏ็ฒต่ชๅฃ่ชๅฐ่ฉฑ๏ผ่ซไฟ็ๆถ้ณ" \
--no-summary
# โโ With AI summary โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
kd config set api-key "AIzaSy..." # Google Gemini (default provider)
kd process "https://youtube.com/watch?v=..."
# Save as Markdown file
kd process "https://youtube.com/watch?v=..." --output notes.md
# โโ Choose a summary style โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
kd process "https://youtube.com/watch?v=..." --style investment
kd process "https://youtube.com/watch?v=..." --style academic
kd process "https://youtube.com/watch?v=..." --style podcast
kd process "https://youtube.com/watch?v=..." --style eli5
# List all available styles
kd styles
# โโ Other AI providers โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
kd process "..." --provider openai --model gpt-4o-mini
kd process "..." --provider anthropic --model claude-haiku-4-5-20251001
Summary Styles
Run kd styles to list all styles. Choose with --style <key>:
| Key | Name | Best For | |
|---|---|---|---|
standard |
๐ | Standard Summary | General videos (default) |
academic |
๐ | Academic Notes | Lectures, research talks, conference papers |
actions |
โ | Action List | Tutorials, how-to guides, step-by-step videos |
news |
๐ฐ | News Brief | Interviews, current events, news commentary |
investment |
๐ | Investment Analysis | Finance, stocks, crypto, macro economics |
podcast |
๐๏ธ | Podcast Digest | Conversations, talk shows, Q&A sessions |
eli5 |
๐ง | Explain Like I'm 5 | Tech, science, academic topics for a general audience |
bullets |
โก | Bullet Notes | Ultra-concise, fast scanning, quick reference |
CLI Reference
`kd process `
Full pipeline: detect subtitles โ transcribe (if needed) โ summarize.
| Flag | Default | Description |
|---|---|---|
--language, -l |
auto-detect | Language code: zh, yue (Cantonese), en, ja, koโฆ |
--style, -s |
standard |
Summary style preset (run kd styles to list all) |
--provider, -p |
google |
AI provider: google | openai | anthropic |
--model, -m |
provider default | AI model name (e.g. gemini-2.5-flash, `gpt-4o-min |
Tools 2
process_videoProcesses a video URL to extract subtitles or transcribe audio and generate a structured summary.list_stylesLists all available summary styles for knowledge articles.Environment Variables
API_KEYAPI key for the chosen AI provider (Google, OpenAI, or Anthropic) if summarization is enabled.