Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Official Code Repo for UniVA: Universal Video Agents
| Date | Stars |
|---|---|
| 2026-07-31 | 517 |
| 2026-08-02 | 517 |
| 2026-08-06 | 517 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# UniVA: Universal Video Agent
# **Towards Open-Source Next-Generation Video Generalist**
<p align="center">
<a href="https://univa.online" target="_blank">
<img src="https://img.shields.io/badge/🏠-Project_Page-orange.svg" alt="Project Page">
</a>
<a href="https://ngrok-univa.chrisprox599.workers.dev/" target="_blank">
<img src="https://img.shields.io/badge/🚀-Demo-rebeccapurple.svg" alt="Demo">
</a>
<a href="https://arxiv.org/abs/2511.08521" target="_blank">
<img src="https://img.shields.io/badge/📄-Paper-brightgreen.svg" alt="Paper">
</a>
<a href="https://huggingface.co/datasets/UniVA-Agent/UniVA-Bench" target="_blank">
<img src="https://img.shields.io/badge/📊-Benchmark-yellow.svg" alt="Benchmark">
</a>
<a href="https://huggingface.co/spaces/UniVA-Agent/UniVA-Leaderboard" target="_blank">
<img src="https://img.shields.io/badge/🏆-Leaderboard-gold.svg" alt="Leaderboard">
</a>
<a href="https://discord.gg/85GkGW897V" target="_blank">
<img src="https://img.shields.io/badge/💬-Discussions-blueviolet.svg" alt="Discussions">
</a>
</p>
<p align="center">
<img src="univa_header.jpg" width="100%" alt="UniVA Header">
</p>
## 🎯 Overview
**UniVA** (Universal Video Agent) is an open-source, next-generation video generalist system that enables you to **plan, compose, and produce** videos through natural language instructions. UniVA acts as your intelligent video director, iterating shots and stories with you through an agentic, proactive workflow.
### ✨ Key Features
#### 🎬 Agentic Creation
- **Multi-round co-creation**: Talk like a director; UniVA iterates shots & stories with you
- **Deep memory & context**: Global + user memory keep preferences, lore, and styles consistent
- **Implicit intent reading**: Understands vague & evolving instructions; less prompt hacking
- **Proactive agent**: Auto plans, checks, and suggests better shots & stories, not just obeys
- **End-to-end workspace**: UniVA plans, calls tools, and delivers full videos
#### 🎥 Omnipotent Video Production Engine
- **Universal video fabric**: Text / Image / Entity / Video → controllable video in one framework
- **Any-conditioned pipeline**: Supports super HD & consistent, cinematic quality with stable identity & objects
- **Complex narratives**: Multi-scene, multi-role, multi-shot stories under structured control
- **Ultra-long & fine-grained editing**: From long-form cuts to per-shot/per-object refinement
- **Grounded by understanding**: Long-video comprehension & segmentation guide generation & edits
#### 🔧 Extensibility
- **MCP-native**: Modular design, easy to extend with new models & tools
- **Industrial quality**: Production-ready video generation capabilities
---
## 🏗️ Architecture
UniVA consists of two main components:
### Backend (Python)
- **Plan Agent**: High-level planning and task decomposition
- **Act Agent**: Execution of specific video generation tasks
- **MCP Tools**: Modular tools for video processing, generation, and editing
- **FastAPI Server**: RESTful API for client communication
### Frontend (Next.js)
- **Web Interface**: User-friendly chat interface
- **Video Editor**: Timeline-based video editing capabilities
- **Project Management**: Save and manage video projects
- **Authentication**: User management and access control
---
## 🚀 Installation
### Prerequisites
- **Python**: 3.10 or higher
- **Node.js**: 18.0 or higher (only if using the web frontend)
- **Bun**: 1.2.18 or higher (only if using the web frontend)
- **CUDA**: Recommended for GPU acceleration (optional but recommended)
### Backend Installation
The backend is the core UniVA agent system. You can use it standalone without the frontend.
#### 1. Clone the Repository
```bash
git clone https://github.com/univa-agent/univa
cd univa
```
#### 2. Install Python Dependencies
```bash
pip install -r requirements_simple.txt
```
And using the project configuration:
```bash
Excerpt of 9,050 characters
Read on GitHub
11
Hao Fei · University of Oxford · United Kingdom
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2beb750ed07ba0f8, llm:Repository description: 'Official Code Repo for UniVA: Universal Video Agents' (language: TypeScript).
matched fp:2beb750ed07ba0f8, llm:Repository description: 'Official Code Repo for UniVA: Universal Video Agents' (language: TypeScript).
matched fp:2beb750ed07ba0f8, llm:Repository description: 'Official Code Repo for UniVA: Universal Video Agents' (language: TypeScript).
matched fp:2beb750ed07ba0f8, llm:Repository description: 'Official Code Repo for UniVA: Universal Video Agents' (language: TypeScript).