Self-Hosting Guide — Run the AI Video Generator Free, 4 Ways
Run Agnes Video Generator on your own computer or server: manual, Docker, npm or AI Agent — pick any one, completely free, no GPU required.
Environment Requirements
Make sure your machine meets these requirements before deploying (skip this if you choose Docker — the image bundles everything):
- Python 3.10+ (required for the manual and npm methods)
- ffmpeg (manual method only; Docker and npm bundle it)
- Node.js 18+ (npm method only)
- Git (for cloning the repository)
- No GPU, no large RAM needed — all AI computation happens in the cloud, a regular laptop is enough
Four Deployment Methods
Pick any one and the service starts; open http://localhost:8765 in your browser.
Method A: Manual deployment (start.sh)
The most traditional way — great if you want to see every step of what happens.
git clone https://github.com/lcy362/agnes-video-generator.git cd agnes-video-generator ./start.sh
The script automatically creates a virtual environment, installs dependencies and opens the browser. Manual start: python3 -m venv .venv && .venv/bin/pip install -r requirements.txt && .venv/bin/python server.py
Method B: Docker deployment
No Python or ffmpeg installation needed — one command to start; images are published to both GHCR and Docker Hub for linux/amd64 and linux/arm64.
docker run -d -p 8765:8765 \ -e AGNES_API_KEY=<your-api-key> \ -v ~/agnes-data/working:/app/.working_dir \ -v ~/agnes-data/config:/app/.agnes_config \ ghcr.io/lcy362/free-short-video:latest
Docker Hub users: replace the image name with lcy362/free-short-video:latest. Always mount both data directories, otherwise your videos and settings are lost when the container is recreated. In PowerShell, replace the \ line continuations with backticks `.
Method C: npm deployment (CLI)
One command starts the entire service — no cloning, no manual environment setup, ffmpeg bundled automatically.
npx free-short-video # Or install globally and run: free-short-video (short alias: fsv) AGNES_API_KEY=<your-api-key> npx free-short-video
Options: --port <n> to change the port, --host 0.0.0.0 for LAN access, --no-open to skip auto-opening the browser. The first run creates a virtual environment and installs dependencies automatically.
Method D: AI Agent assisted deployment
The project is designed for AI coding assistants — let an Agent handle the deployment for you.
git clone https://github.com/lcy362/agnes-video-generator.git cd agnes-video-generator # Then tell your AI agent: "Read this project's AGENTS.md, install dependencies, configure the API key, and start the service."
The project ships an AGENTS.md deployment guide with a four-layer verification checklist that the Agent runs through and reports on.
How to Verify Deployment
- The browser opens (or you visit) http://localhost:8765 — seeing the Agnes Video Generator UI means success
- Paste your free API key at the top of the page and start generating
- Timing reference: simple video ≈ 1–3 min, creative long video (5 scenes) ≈ 10–20 min
Usage Tips
- Resume: after an interruption, restart the service and click 'Resume' on the unfinished task in the task list
- Output directory: all artifacts live in .working_dir/{timestamp}_{task_id}/; final_video.mp4 is the final video (with narration and subtitles)
- Port busy: if port 8765 is taken, run lsof -ti:8765 | xargs kill on macOS/Linux; on Windows use netstat -ano | findstr :8765 to find the PID, then taskkill
- There is a rate limit of 16 API calls per minute — it keeps the service free; it is not your computer being slow
Don't want to install?
Open the official website and try it online for free — no installation needed.
Try it online →Related Pages
Get a Free Agnes AI API Key — 3-Minute Setup | Free AI Video Guide
Agnes AI API keys are completely free: full steps to register, create and copy, three configuration methods (Web UI / env var / API), and 401 troubleshooting.
Text to Video API — Free AI Video Generation API, No GPU | Agnes Video
Programmatically access Agnes AI's free video models. Text-to-video, image-to-video, and narration APIs. Developer-friendly, zero-cost, no high-end GPU required.
Quick Start: Free AI Video Generation Guide
From getting a free API key to generating your first AI video — a step-by-step guide to Agnes Video Generator.
Deployment Documentation
The four deployment methods here (manual / Docker / npm / AI agent) follow the project repo and the official docs below.
- agnes-video-generator — 开源 AI 视频生成项目lcy362 · GitHub (2026)
Deployment scripts like start.sh/server.py and the default port (8765) follow the open-source repository.
- FFmpeg Documentation — 音视频处理官方文档FFmpeg 项目 · ffmpeg.org (2025)
The ffmpeg dependency for manual deployment is covered in the official FFmpeg documentation.
- Docker Documentation — 容器化部署Docker · docs.docker.com (2025)
Building and running the Docker image follows the official Docker documentation.
- Node.js — JavaScript 运行时文档OpenJS Foundation · nodejs.org (2025)
The Node.js 18+ requirement for the npm method is documented on the official Node.js site.
Why you can trust this
Written by a practicing developer and cross-checked against authoritative primary sources such as arXiv papers, vendor technical reports, and the Stanford AI Index.
SandGrid@lcy362
Author of Agnes Video Generator · Full-stack Developer
Independent developer and author of Agnes Video Generator, an open-source (MIT) AI video generation tool built on Agnes AI's free video models. Has helped 1,000+ creators produce AI videos at zero cost. Focused on making video generation models accessible and production-ready; content is based on hands-on practice and primary research.
View on GitHubLast updated：2026-08-21
Ready to Start Creating?
"Making world-class AI belong to everyone." — Bruce Yang. It's completely free, no credit card, and you won't need a high-end GPU. Your first AI video starts at zero cost. Want to use Agnes AI's free video models? This is the easiest way in.
Clone the GitHub repo and launch in 2 minutes