StanfordSNR/puffer

Puffer is a free live TV streaming website and a research study at Stanford using machine learning to improve video streaming

40
/ 100
Emerging

Puffer combines real-time video delivery with adaptive bitrate selection powered by machine learning models trained on actual viewing conditions. The system uses FFmpeg for encoding and custom congestion control algorithms that learn optimal streaming parameters across diverse network conditions. It integrates with standard MPEG-DASH protocols and collects anonymized telemetry from live streaming sessions to continuously improve prediction accuracy.

901 stars.

No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 1 / 25
Community 23 / 25

How are scores calculated?

Stars

901

Forks

138

Language

C++

License

Last pushed

Nov 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/StanfordSNR/puffer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.