Skip to content

hypit-ai /hypit

A language that lets your coding agent clone and re-run short videos
Video frameworkCustom licenseEnglish README
Stars
19k
30 days
+151
Last push
yesterday
hypit screenshot from its README
From the hypit README on GitHub.

About hypit

Hypit gives your coding agent a language for building short videos. Drop in a reference video and the agent clones it into an editable workflow. You get footage, captions, B-roll and effects, timed to words, not seconds. You'll need a coding agent, and model services bill you separately.

Best for: Growth teams who want an agent to clone a winning short-video format and mass-produce variants.

What it does

  • Clones a dropped-in video into a full workflow: footage, captions, B-roll, effects
  • Compiles SVML source into a rendered video you can edit and re-run
  • Reuses one composition for many variants, generating only what changed
  • Lets you swap a host without touching the captions
  • Aligns captions to single words and tells speakers apart in interviews
  • Renders code-driven visuals locally, with no generation model calls

Quickstart

Rewritten from the README. Check the repo for the latest steps.

  1. 1
    Install the skill with the command below.
    npx skills add hypit-ai/hypit -g
  2. 2
    Open a session in any empty or existing project folder with your coding agent.
  3. 3
    Ask the agent to clone a video, e.g. the command below.
    /hypit Clone this video: /path/to/video.mp4
  4. 4
    Or start from scratch, e.g. the command below
    /hypit Make a ranking video that puts Hypit in S tier.
  5. 5
    Let the agent check the environment, ask for credentials, generate material and build the composition.

Models and languages

Models it works with

  • Seedance 2 Mini 720p
  • GPT Image 2
  • WhisperX
  • Google Video Intelligence
  • YOLOv8 AnimeFace

Interface and docs

  • English
  • Chinese

Alternatives

Other video framework projects people compare with hypit.

Orkas-AI

Orkas-VideoStudio

Editable video plans from a plain-language brief, rendered by your coding agent

Video framework
  • Seedance
  • Kling v2.1
  • Atlas Cloud
  • +3
497 GitHub stars10 days agoMIT

calesthio

OpenMontage

Video studio that your AI coding assistant runs

Video framework
  • Google Veo
  • Kling
  • Seedance 2.0
  • +7
62k GitHub stars+104/30d26 days agoAGPL-3.0

HKUDS

ViMax

Multi-shot AI video from an idea, a script, or a novel chapter

Video framework
  • Seedance 2.0 Fast
  • GPT Image 2
  • Google Omni
  • +4
13k GitHub stars+3/30d2 days agoMIT

harry0703

MoneyPrinterTurbo

Writes a narrated short video from a topic: script, voiceover, footage, subtitles

Video framework
  • MiniMax H3
  • Seedance
  • Wan
  • +7
128k GitHub stars+127/30dyesterdayMIT

Featured on OpenMicroDrama

Do you maintain hypit? Add this badge to your README so English speakers can find our write-up.

Featured on OpenMicroDrama
markdown
[![Featured on OpenMicroDrama](https://openmicrodrama.com/badges/featured.svg)](https://openmicrodrama.com/projects/hypit-ai-hypit)

The badge links to this page. Want your description changed? Email support@openmicrodrama.com.

Reviewed Oct 1, 2026. Custom license based on Apache 2.0 with extra conditions. Read it before redistributing. The repo points you to HypiHub, the project's own paid hosted model service, but you can connect your own API or local models. We write these descriptions ourselves. The repo's own docs are the final word.