GetStream/Vision-Agents
Open Vision Agents by Stream is a platform for building real-time, low-latency multi-modal AI agents that understand and interact with video content using advanced models and Stream's edge network.
Awesome AI Agents › Video Processing Agents
StreamRAG is a powerful video search and streaming agent designed to enhance video content accessibility and interaction through GPT-powered technology. It allows developers to upload multiple videos to create a searchable library or collection, enabling users to perform real-time searches across these videos and receive video responses or compilations. This functionality is particularly useful for extracting key insights, summarizing content, and retrieving specific information from video materials efficiently. The project supports publishing searchable video collections on the ChatGPT store, making it easy to share and access curated video content. Users can receive summarized text answers using Retrieval-Augmented Generation (RAG) techniques, which combine retrieval of relevant video segments with natural language generation to provide concise and informative responses. This feature is ideal for users seeking quick highlights or detailed points from specific video episodes or segments. StreamRAG offers a straightforward setup process, including obtaining an API key from the VideoDB console, installing necessary dependencies, uploading video collections, and running a local Flask server. The project also provides guidance on publishing the service on the ChatGPT store, allowing developers to create custom GPTs that integrate video search capabilities. Future development plans include adding support for popular backend deployment platforms like Heroku and Replit, integrating with additional data sources such as Dropbox and Google Drive, and connecting with meeting recorder APIs like Zoom, Teams, and Recall.ai. These enhancements aim to broaden the usability and integration options for StreamRAG. Overall, StreamRAG is a versatile tool for developers and content creators looking to leverage AI-driven video search and summarization, facilitating more interactive and efficient video content consumption.
https://github.com/video-db/StreamRAG
Open Vision Agents by Stream is a platform for building real-time, low-latency multi-modal AI agents that understand and interact with video content using advanced models and Stream's edge network.
ShortGPT is an AI-powered framework that automates video content creation and editing for platforms like YouTube Shorts and TikTok, supporting multi-language voiceovers and automated footage sourcing.
A curated list of recent diffusion models and resources for video generation, editing, restoration, and various AI-driven video applications.
Source-available AIGC video production pipeline that turns a manuscript into a finished short drama, handling character extraction, episode planning, scripts, storyboards, voice-over and final editing.
Apache-2.0 toolkit that lets local coding agents turn HTML, CSS and data into real MP4 video through pluggable render engines, 21 animated templates and an optional AI soundtrack.
Multi-agent framework for video understanding, editing and generation that parses user intent, builds a graph-based tool workflow and produces edited or newly created videos from natural language.
Director is an AI video agents framework that enables complex video tasks like search, editing, and generation through natural language commands and real-time streaming, built on VideoDB's video-as-data infrastructure.
Microsoft research agent for long-form video question answering that treats segmented clips as an environment and iteratively selects multi-granular search tools, reaching state of the art on LVBench.