Skip to content

redcappp/yt-ai-agent

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

YT AI Agent

YT AI Agent is a background YouTube automation system for AI/productivity channels. It analyzes trend signals, reads channel analytics, plans upload timing, generates narrated Shorts/videos, writes metadata, and uploads through the official YouTube APIs.

YT AI Agent banner

Highlights

  • Trend scanner for configured niches and seed keywords.
  • YouTube Analytics reader for recent channel performance.
  • Upload-hour scoring using recent video performance.
  • Automatic Shorts and long-form video generation with scripts, narration, rendered slides, metadata, and queues.
  • Official YouTube Data API upload pipeline.
  • Windows startup-task scripts for unattended background operation.
  • Status reporting through data/status.json and channel reports.

Live Channel Snapshot

The latest local verification reported:

Activity: Sleeping
Next cycle: 900 seconds
Ready Shorts: 5 locally queued, 3 reported in latest agent status
Ready Videos: 1
Next upload: 2026-06-04 07:00:00
Best upload hours: 18, 7, 17, 19
28-day views: 238
28-day watch time: 12 minutes
Recent uploads analyzed: 35
Underperforming uploads flagged for metadata rescue: 10
Verified generated Short: 1080x1920 H.264/AAC, 32 seconds
Creative providers: Gemini configured but quota-limited, Hugging Face authenticated, Ollama fallback working

Runtime databases, OAuth tokens, logs, and generated video queues are intentionally excluded from GitHub.

Tech Stack

  • Python
  • YouTube Data API v3
  • YouTube Analytics API
  • SQLite
  • Windows SAPI text-to-speech
  • Movie/rendering utilities
  • Optional LLM providers: Ollama, Gemini, OpenRouter, OpenAI-compatible endpoints, Pollinations

Quick Start

  1. Create a Google Cloud project.
  2. Enable YouTube Data API v3 and YouTube Analytics API.
  3. Create OAuth Desktop credentials and place them in secrets/client_secret.json locally.
  4. Copy .env.example to .env and fill local keys.
  5. Install dependencies:
python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -r requirements.txt
  1. Authenticate and run:
python -m yt_ai_agent auth
python -m yt_ai_agent run

Project Structure

yt_ai_agent/      Core agent modules
scripts/          Startup install/uninstall scripts
brand/            Public channel branding assets
reports/          Local analytics/trend reports, ignored by default
content/          Local video queues, ignored by default
data/             Local state/status, ignored by default
secrets/          OAuth credentials, ignored

Safety Notes

The project uses official APIs and keeps secrets out of source control. You are responsible for YouTube policy compliance and rights to uploaded content.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors