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
RayVentura/ShortGPT
ShortGPT is an innovative AI-driven framework designed to automate the creation of video content, particularly optimized for platforms like YouTube Shorts and TikTok. It streamlines the entire video production process, from script generation and footage sourcing to voiceover synthesis and video editing, making content creation more efficient and accessible. The framework supports multiple languages for voiceover, including English, Spanish, Arabic, French, Polish, German, Italian, Portuguese, Russian, Mandarin Chinese, Japanese, Hindi, Korean, and over 30 more languages using EdgeTTS technology. ShortGPT integrates various technologies such as Moviepy for video editing, OpenAI for script and prompt generation, ElevenLabs and EdgeTTS for voice synthesis, and Pexels and Bing Image for sourcing background footage and images. It features several specialized engines: the ContentShortEngine for creating short videos with metadata, the ContentVideoEngine for longer videos with audio and background footage, and the ContentTranslationEngine for dubbing and translating videos into different languages with captions. The framework uses an automated EditingEngine that employs an Editing Markup Language and JSON to break down the editing process into manageable blocks understandable by large language models. ShortGPT also ensures long-term persistency of editing variables using TinyDB. It offers a web interface via Gradio and can be run locally using Docker or through a Google Colab notebook for ease of use without installation. The project is open-source and encourages contributions to enhance features, infrastructure, and documentation. Overall, ShortGPT is a flexible and powerful tool for automating creative video content production, making it ideal for content creators looking to scale their output on social media platforms.
https://github.com/RayVentura/ShortGPT
Also in Video Processing Agents
showlab/Awesome-Video-Diffusion
A curated list of recent diffusion models and resources for video generation, editing, restoration, and various AI-driven video applications.
dramaclaw/dramaclaw
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.
nexu-io/html-video
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.
HKUDS/VideoAgent
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.
video-db/Director
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.
video-db/StreamRAG
StreamRAG is a GPT-powered video search and streaming agent that enables real-time video search, summarization, and publishing of searchable video collections on the ChatGPT store.
microsoft/DeepVideoDiscovery
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.