VideoRAG
Ask questions across long videos with multimodal retrieval and scene-level context.
- Stars
- 3,156
- Forks
- 446
- Updated
- Updated Jul 14, 2026
Ask questions across long videos with multimodal retrieval and scene-level context.
VideoRAG is an open-source framework for retrieving and answering questions over long-form video, with the Vimo desktop interface for importing one or more videos and chatting about their contents. It also includes the LongerVideos benchmark and evaluation code for researchers working on long-context video understanding. Prebuilt Vimo downloads are still marked as coming soon, so current users generally need to start the Python backend and Electron frontend from source.
Resource types
Use cases
Audience
Public GitHub facts last synced Jul 14, 2026.
Use LibVLC playback, streaming, and encoding inside .NET applications.
Verify and configure HEVC decoding and encoding in Chromium-based browsers and Electron.
Deploy a Docker stack for media requests, downloads, streaming, and optional AI recommendations.
Automate and test Chromium, Firefox, and WebKit through one API.