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
video-db/Director
Director is an advanced AI video agents framework designed to revolutionize video interactions and workflows by enabling complex video tasks such as search, editing, compilation, and generation with instant streaming of results. It is built on top of VideoDB's innovative 'video-as-data' infrastructure, which provides a reliable and scalable foundation for cloud storage, indexing, and streaming of video content. The framework acts like a ChatGPT for videos, allowing users to issue natural language commands that the system intelligently interprets and executes by orchestrating multiple specialized agents. For example, a command like "Upload this video and send the highlights to my Slack" triggers a series of coordinated actions by different agents to complete the task seamlessly. Key features include over 20 pre-built customizable video agents capable of summarizing videos quickly, generating full movies with voiceovers from scripts, searching and indexing media libraries, organizing and clipping content, dubbing and editing audio and video, translating and adding subtitles in any language, and more. The framework offers a sleek chat-based interface with integrated video playback and intuitive controls, providing a personal assistant-like experience for media management. Director integrates with various GenAI APIs, large language models, and databases, allowing users to mix and match powerful AI tools to enhance their video workflows. Its modular and flexible architecture supports running locally or on the cloud, making it suitable for developers, creators, and teams aiming to simplify media workflows and unlock new creative possibilities. The core of Director is its Reasoning Engine, which drives intelligent decision-making and dynamic workflows by understanding context, orchestrating multiple agents, and breaking down tasks into smaller steps for real-time collaboration and accurate results. The system provides live progress updates and is extensible to include custom logic or connect to external APIs. Overall, Director is a comprehensive and innovative framework that transforms how users interact with video content, making complex video tasks accessible and efficient through AI-powered agents and conversational interfaces.
https://github.com/video-db/Director
Also in Video Processing Agents
RayVentura/ShortGPT
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.
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/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.