Skip to content

armgit / hypit

Public Imported from GitHub
0

Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.

docs: move overview above star section

rpone442ac574c8ed
diff --git a/README.md b/README.md
index 35fa8a00..647772c1 100644
--- a/README.md
+++ b/README.md
@@ -49,25 +49,6 @@ Hypit gives AI agents (Claude Code, Codex...) a language and system to create vi
npx skills add hypit-ai/hypit -g
```
-## Why Hypit
-
-- **Clone any video:** drop in a video, get the whole workflow — footage, captions, B-roll, effects. Not a script breakdown.
-- **One workflow, 100 variants:** the second video costs almost nothing; the hundredth is a loop.
-- **Pluggable components:** swap the host without touching the captions. Use the library, fork it, or write your own.
-- **Open source, $0:** no seat pricing, no per-render fees, no watermark. Arcads charges $220/mo, Creatify $39, before you render anything — but Hypit is $0.
-
-## What Hypit Can Build
-
-Drop in a video and your agent clones the whole workflow — or describe what you want and it writes one from scratch. Either way you get an editable, re-runnable composition, not a one-off render.
-
-- **Paid social ads** — clone a winning ad from the Meta Ad Library, swap in your product, ship 50 hook variants the same day. When it fatigues in two weeks, re-run with fresh openings; the body never changes.
-- **Viral clones** — any TikTok, Reel, or Short becomes a template. Swap the host, the hook, the product, the language, the aspect ratio.
-- **TikTok Shop and affiliate videos** — one format that converts, a new SKU every day. Swap the product, the price, the CTA; the structure that worked stays untouched.
-- **AI UGC and talking heads** — narration, word-level captions, B-roll, comment stickers, beat-synced cuts, all wired automatically.
-- **Podcast and interview clips** — split-screen layouts, speaker-aware captions, reaction overlays.
-- **Code-rendered videos** — visuals driven entirely by front-end code. Compiled from source, zero API calls, 0 dollars a video.
-- **Localized versions** — the same video in ten languages. Rewrite a line and the timing re-flows itself.
-
## Examples
### UGC
@@ -147,6 +128,25 @@ Or start without a reference video:
Your agent can check the environment, request only the credentials the video needs, preview the result, and build it.
+## Why Hypit
+
+- **Clone any video:** drop in a video, get the whole workflow — footage, captions, B-roll, effects. Not a script breakdown.
+- **One workflow, 100 variants:** the second video costs almost nothing; the hundredth is a loop.
+- **Pluggable components:** swap the host without touching the captions. Use the library, fork it, or write your own.
+- **Open source, $0:** no seat pricing, no per-render fees, no watermark. Arcads charges $220/mo, Creatify $39, before you render anything — but Hypit is $0.
+
+## What Hypit Can Build
+
+Drop in a video and your agent clones the whole workflow — or describe what you want and it writes one from scratch. Either way you get an editable, re-runnable composition, not a one-off render.
+
+- **Paid social ads** — clone a winning ad from the Meta Ad Library, swap in your product, ship 50 hook variants the same day. When it fatigues in two weeks, re-run with fresh openings; the body never changes.
+- **Viral clones** — any TikTok, Reel, or Short becomes a template. Swap the host, the hook, the product, the language, the aspect ratio.
+- **TikTok Shop and affiliate videos** — one format that converts, a new SKU every day. Swap the product, the price, the CTA; the structure that worked stays untouched.
+- **AI UGC and talking heads** — narration, word-level captions, B-roll, comment stickers, beat-synced cuts, all wired automatically.
+- **Podcast and interview clips** — split-screen layouts, speaker-aware captions, reaction overlays.
+- **Code-rendered videos** — visuals driven entirely by front-end code. Compiled from source, zero API calls, 0 dollars a video.
+- **Localized versions** — the same video in ten languages. Rewrite a line and the timing re-flows itself.
+
## Stay Tuned with Us
Star us, and you will receive all release notifications from GitHub without any delay!
diff --git a/README.zh-CN.md b/README.zh-CN.md
index c348c423..1a561721 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -49,25 +49,6 @@ Hypit 为 AI Agent(Claude Code、Codex 等)提供了一套制作视频的语
npx skills add hypit-ai/hypit -g
```
-## 为什么选择 Hypit
-
-- **真的能 Clone:**丢一条视频进来,拿到整份 workflow —— 画面、字幕、B-roll、特效。不是拆解脚本。
-- **一份 workflow,100 个变体:**第二条几乎不花钱,第一百条只是跑个循环。
-- **可插拔组件:**换主播不动字幕。用组件库、fork 一个,或自己写。
-- **开源,一条视频 0 元:**不按人头收费,不按条收费,没有水印。Arcads 每月 220 美元,Creatify 39 美元,而这是你还没渲染任何东西之前 —— 但 Hypit 是 0 元。
-
-## Hypit 能构建什么
-
-丢一条视频进来,Agent 把整套 workflow 克隆下来;或者直接描述你想要的视频,让它从零写一份。拿到的都是可编辑、可重跑的工作流,而不是一次性的成片。
-
-- **信息流广告** —— 从 Meta 广告库拉一条正在跑的广告,克隆成 workflow,换上你的产品,当天发出 50 个 Hook 变体。两周后创意衰退,换一批开头重跑,主体一个字不动。
-- **复刻爆款** —— 任何 TikTok、Reels、Shorts 都能变成模板:换主播、换 Hook、换产品、换语言、换画幅。
-- **带货视频** —— 一个跑通的格式,每天换一个 SKU。换产品、换价格、换 CTA,转化率跑出来的结构原封不动。
-- **AI UGC 与口播** —— 配音、词级字幕、B-roll、评论区贴纸、卡点剪辑,全部自动挂好。
-- **播客与采访切片** —— 分屏布局、区分说话人的字幕、反应特效。
-- **代码渲染的视频** —— 画面完全由前端代码驱动。全部由源码编译,零 API 调用,一条 0 元。
-- **多语言版本** —— 同一条视频十种语言。改一句台词,时间轴自己重排。
-
## 示例
### UGC
@@ -146,6 +127,25 @@ npx skills add hypit-ai/hypit -g
Agent 会检查环境,只索要这条视频需要的凭据,先给出预览,再执行构建。
+## 为什么选择 Hypit
+
+- **真的能 Clone:**丢一条视频进来,拿到整份 workflow —— 画面、字幕、B-roll、特效。不是拆解脚本。
+- **一份 workflow,100 个变体:**第二条几乎不花钱,第一百条只是跑个循环。
+- **可插拔组件:**换主播不动字幕。用组件库、fork 一个,或自己写。
+- **开源,一条视频 0 元:**不按人头收费,不按条收费,没有水印。Arcads 每月 220 美元,Creatify 39 美元,而这是你还没渲染任何东西之前 —— 但 Hypit 是 0 元。
+
+## Hypit 能构建什么
+
+丢一条视频进来,Agent 把整套 workflow 克隆下来;或者直接描述你想要的视频,让它从零写一份。拿到的都是可编辑、可重跑的工作流,而不是一次性的成片。
+
+- **信息流广告** —— 从 Meta 广告库拉一条正在跑的广告,克隆成 workflow,换上你的产品,当天发出 50 个 Hook 变体。两周后创意衰退,换一批开头重跑,主体一个字不动。
+- **复刻爆款** —— 任何 TikTok、Reels、Shorts 都能变成模板:换主播、换 Hook、换产品、换语言、换画幅。
+- **带货视频** —— 一个跑通的格式,每天换一个 SKU。换产品、换价格、换 CTA,转化率跑出来的结构原封不动。
+- **AI UGC 与口播** —— 配音、词级字幕、B-roll、评论区贴纸、卡点剪辑,全部自动挂好。
+- **播客与采访切片** —— 分屏布局、区分说话人的字幕、反应特效。
+- **代码渲染的视频** —— 画面完全由前端代码驱动。全部由源码编译,零 API 调用,一条 0 元。
+- **多语言版本** —— 同一条视频十种语言。改一句台词,时间轴自己重排。
+
## 关注我们
给我们点个 Star,即可第一时间收到 GitHub 的所有版本发布通知!