Transcript archive of Nate Jones YouTube videos.
- Videos Downloaded: 431 / 428 (100% + retries)
- Date Range: May 21, 2024 - Jan 14, 2026
- Last Updated: Jan 16, 2026
nate-jones-transcripts/
├── README.md
├── index.json # Master index of all videos
├── index/ # Topic-based index (111 topics)
│ ├── README.md # All topics with episode counts
│ ├── ai-agents.md # Episodes about AI agents
│ ├── anthropic.md # Episodes mentioning Anthropic
│ ├── claude.md # Episodes about Claude
│ ├── openai.md # Episodes about OpenAI
│ └── ... # 100+ more topic files
├── episodes/
│ └── YYYY-MM-DD-video-title/
│ └── transcript.md # YAML frontmatter + full transcript
└── scripts/
├── download.py # Download script (uses Supadata API)
├── enrich.py # AI enrichment (entities, topics, etc.)
├── create_index.py # Generates index.json
└── build_index.py # Builds topic index files
Each transcript.md contains:
---
title: "Video Title"
video_id: "abc123"
youtube_url: "https://www.youtube.com/watch?v=abc123"
substack_url: "https://natesnewsletter.substack.com/p/..."
publish_date: "2026-01-14"
duration: "32:18"
view_count: 107305
yt_tags:
- "AI agents"
- "Claude"
# AI-enriched metadata
content_type: "Tutorial" # News Roundup, Deep Dive, Tutorial, Framework, Opinion, Case Study
primary_topic: "AI Tools" # AI Agents, AI Strategy, AI Tools, Career, Prompting, AI News
difficulty: "Advanced" # Beginner, Intermediate, Advanced
audience:
- "Engineers"
- "Executives"
entities:
companies:
- "OpenAI"
- "Anthropic"
people:
- "Sam Altman"
products:
- "Claude"
- "ChatGPT"
models:
- "GPT-4"
- "Claude 3.5"
concepts:
- "Key insight extracted from transcript"
summary:
- "First key point"
- "Second key point"
---
# Video Title
[Full transcript text here]Browse episodes by topic via the index/ folder:
Top Topics:
- AI Tools (311 episodes)
- AI Strategy (284 episodes)
- AI News (267 episodes)
- Anthropic (204 episodes)
- Claude (199 episodes)
- OpenAI (176 episodes)
- AI Agents (171 episodes)
grep -r "Claude Code" episodes/import json
with open('index.json') as f:
data = json.load(f)
for video in data['videos']:
print(f"{video['publish_date']}: {video['title']}")# Find all tutorials for engineers
tutorials = [v for v in data['videos']
if v.get('content_type') == 'Tutorial'
and 'Engineers' in v.get('audience', [])]
# Find videos mentioning Anthropic
anthropic_vids = [v for v in data['videos']
if 'Anthropic' in v.get('entities', {}).get('companies', [])]# Set your Supadata API key
export SUPADATA_API_KEY="your_key_here"
# Download next batch
python download.py 100- Content by Nate Jones
- Transcripts via Supadata API