#5858th of 75 in Image and videoFor image, video and design, video and animation
html-video
Turns prompts, articles or repos into MP4 videos via a local coding agent
- Stars
- 4.8k
- License
- Apache-2.0
- Last commit
- Jun 2026
- Language
- HTML
5 on 26 May 20264,832 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
html-video has a local coding agent write a storyboard and one animated HTML frame per scene. Each frame is recorded in headless Chromium and the frames are concatenated into an MP4 with ffmpeg (libx264). It ships a browser studio on port 3071, a CLI, 21 license-tagged templates, and optional MiniMax music and narration. Only the Hyperframes engine is implemented; Remotion, Motion Canvas and Revideo adapters are planned.
Who it is for: Developers who want agent-written HTML animations rendered to MP4 locally
Strengths
- Renders MP4 locally with headless Chromium and ffmpeg; no per-render fees
- Supports 14 agent backends, auto-detected on PATH, plus the Anthropic API
- Builds multi-scene videos from a URL or GitHub repo fetched server-side
- Templates carry YAML manifests with SPDX license and attribution flags
Weaknesses
- Only the Hyperframes engine works; other engine adapters are roadmap items
- Needs Node 20+, pnpm 9+, ffmpeg and Playwright Chromium installed manually
- Soundtrack requires a MiniMax API key from a third-party service
- No release published and no Docker setup; build from source with pnpm
What it needs
- no GPU
- Needs Node.js 20+, pnpm 9+, ffmpeg, Chromium (Playwright), a coding agent CLI or Anthropic API key, MiniMax API key (optional)
- Models: Claude Code, Codex CLI, Gemini CLI, Cursor Agent, Qwen Code
- port 3071
Also in Image and video
See all 75| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 93 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 87 out of 100 |
| #4 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 86 out of 100 |
| #5 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |