GetStream/Vision-Agents

Open Vision Agents by Stream. Build Vision Agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

73
/ 100
Verified

This project helps you build AI assistants that can watch and understand live video and audio, responding in real-time. It takes live video and audio feeds and combines them with advanced AI models to produce intelligent insights or interactions, like real-time coaching or anomaly detection. This is for developers building interactive AI applications that require immediate understanding and response to visual and auditory cues.

7,366 stars. Actively maintained with 46 commits in the last 30 days. Available on PyPI.

Use this if you need to create multi-modal AI agents that can watch, listen, and understand live video streams with ultra-low latency for applications like sports coaching, drone monitoring, or virtual assistants.

Not ideal if your application does not require real-time video and audio processing or if you're not comfortable integrating various AI models and services.

real-time video analysis AI coaching live monitoring video analytics interactive AI experiences
Maintenance 20 / 25
Adoption 10 / 25
Maturity 24 / 25
Community 19 / 25

How are scores calculated?

Stars

7,366

Forks

574

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

46

Dependencies

10

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/GetStream/Vision-Agents"

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