AutoClip vs AutoShorts (JayWebtech) vs OpenShorts

Side by side, as alternatives to Opus Clip. Rows that differ are highlighted; the strongest value in a row is marked. Unknown means no source yet.

AutoClipzhouxiaoka/autoclip

AutoShorts (JayWebtech)JayWebtech/autoshorts

OpenShortsmutonby/openshorts

Opus Clippaid product

Cost and coverage

Price

$0 software; you run it

See pricing page source ↗

AI picks highlight clips from a long video

Partly

Yes

Auto-reframe to vertical 9:16 (speaker or face tracking)

Partly

Yes

Animated burned-in captions on clips

Partly

Yes

Virality score per clip

Yes

Schedule and publish clips to social platforms

Partly

Yes

Jobs covered

4 of 5 jobs

2 of 5 jobs

4 of 5 jobs

All 5

Popularity and activity (from GitHub)

Stars

9,601Top

1,277

6,909

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

335Top

—

Latest release

v1.5.6 · 2026-10-09Top

v0.1.5 · 2026-07-01

Unknown

—

Commits / 12 wk

415

260

—

People committing / 12 mo

—

Issues opened / closed, 30 days

62 / 66

4 / 0

7 / 9

—

Facts, with sources on each project page

Runs on my machine?Differs

Yes, desktop app, Docker web UI or CLI; cutting and rendering always local

Yes, desktop app; fully offline mode with Ollama and local Whisper

Yes, self-hosted with Docker Compose; a paid hosted version also exists

Hosted by the vendor

Code licenceDiffers

MIT

MIT for the core app; the cloud/ folder (billing, hosted infrastructure) is source-available under a commercial licence

—

Model weights licenceDiffers

No separate model weights; uses the Whisper/SenseVoice and LLM models you configure

No bundled weights; uses the Ollama, Whisper or cloud models you choose

No separate model weights; downloads third-party models (faster-whisper, YOLOv8, MediaPipe) and calls the LLM you choose

—

Commercial useDiffers

Yes, MIT code; terms of your chosen model providers apply

No licence granted for the code, so reuse or redistribution is not permitted by default

Yes for the MIT core; the cloud/ billing folder may not be resold as a hosted service. Licences of bundled models (e.g. ultralytics YOLOv8) not checked

—

Paid services needed?Differs

None required with Ollama / LM Studio and local Whisper; cloud LLM, cloud ASR, AI images and publishing services are optional

Not required (Ollama + local Whisper); the recommended setup uses paid Deepgram and DeepSeek or Claude APIs

Clipping can run with a local LLM and no paid key; Gemini is the default and is needed for auto-layout and silent videos; posting, dubbing and AI actors use paid APIs

Subscription

HardwareDiffers

Desktop app: Apple Silicon Mac with macOS 13 or newer (Intel Macs not supported), or Windows 10/11 x64; no RAM or GPU figures

Not documented; FFmpeg must be on PATH

8GB+ RAM; CPU works (5-8 min per 8-min video); optional NVIDIA GPU, 8GB VRAM enough for large-v3-turbo

—

Operating systemsDiffers

Desktop for Windows 10/11 x64 and macOS Apple Silicon; Intel Macs and Linux via Docker or CLI

macOS (Apple Silicon and Intel), Windows, Linux (.deb, .rpm, AppImage)

Runs in Docker; Linux and Windows (Docker Desktop with WSL2) are documented; macOS not mentioned

—

Setup effortDiffers

Easy, desktop installers (.dmg / -setup.exe) with Python and FFmpeg bundled; Docker or pip for CLI

Easy; unsigned installers from GitHub Releases plus FFmpeg on PATH

Medium, docker compose up --build, then enter API keys in the dashboard

—

Stars over time

Switch to Growth % to compare projects of different sizes fairly.

AutoClip
AutoShorts (JayWebtech)
OpenShorts

Focus a point, use arrow keys, or tap for its value.

Tracked daily since 16 Oct 2026. Dashed history: estimated from public records of when people starred the repo. Lines connect observations only; gaps contain no measured points.

Growth % starts at each project's first observed point in the shown range. Zero-star starts are unavailable.

Notes for a video or post

A plain summary with today's date and a link to the sources. Check each project page before you publish.

AutoClip vs AutoShorts (JayWebtech) vs OpenShorts (as alternatives to Opus Clip)
Figures from RepoQuarry, 21 Oct 2026. Sources: https://repoquarry.dev/compare?ids=autoclip,autoshorts,openshorts&product=opus-clip

Opus Clip: See pricing page
AutoClip: free software; does 4 of 5 Opus Clip jobs
AutoShorts (JayWebtech): free software; does 2 of 5 Opus Clip jobs
OpenShorts: free software; does 4 of 5 Opus Clip jobs

- AutoClip: 9,601 GitHub stars, 415 commits in 12 weeks, licence MIT
- AutoShorts (JayWebtech): 1,277 GitHub stars, 8 commits in 12 weeks, licence No licence; all rights reserved by default
- OpenShorts: 6,909 GitHub stars, 260 commits in 12 weeks, licence MIT for the core app; the cloud/ folder (billing, hosted infrastructure) is source-available under a commercial licence

Where they differ:
- Runs on my machine?: AutoClip Yes, desktop app, Docker web UI or CLI; cutting and rendering always local; AutoShorts (JayWebtech) Yes, desktop app; fully offline mode with Ollama and local Whisper; OpenShorts Yes, self-hosted with Docker Compose; a paid hosted version also exists
- Code licence: AutoClip MIT; AutoShorts (JayWebtech) No licence; all rights reserved by default; OpenShorts MIT for the core app; the cloud/ folder (billing, hosted infrastructure) is source-available under a commercial licence
- Model weights licence: AutoClip No separate model weights; uses the Whisper/SenseVoice and LLM models you configure; AutoShorts (JayWebtech) No bundled weights; uses the Ollama, Whisper or cloud models you choose; OpenShorts No separate model weights; downloads third-party models (faster-whisper, YOLOv8, MediaPipe) and calls the LLM you choose
- Commercial use: AutoClip Yes, MIT code; terms of your chosen model providers apply; AutoShorts (JayWebtech) No licence granted for the code, so reuse or redistribution is not permitted by default; OpenShorts Yes for the MIT core; the cloud/ billing folder may not be resold as a hosted service. Licences of bundled models (e.g. ultralytics YOLOv8) not checked
- Paid services needed?: AutoClip None required with Ollama / LM Studio and local Whisper; cloud LLM, cloud ASR, AI images and publishing services are optional; AutoShorts (JayWebtech) Not required (Ollama + local Whisper); the recommended setup uses paid Deepgram and DeepSeek or Claude APIs; OpenShorts Clipping can run with a local LLM and no paid key; Gemini is the default and is needed for auto-layout and silent videos; posting, dubbing and AI actors use paid APIs
- Hardware: AutoClip Desktop app: Apple Silicon Mac with macOS 13 or newer (Intel Macs not supported), or Windows 10/11 x64; no RAM or GPU figures; AutoShorts (JayWebtech) Not documented; FFmpeg must be on PATH; OpenShorts 8GB+ RAM; CPU works (5-8 min per 8-min video); optional NVIDIA GPU, 8GB VRAM enough for large-v3-turbo
- Operating systems: AutoClip Desktop for Windows 10/11 x64 and macOS Apple Silicon; Intel Macs and Linux via Docker or CLI; AutoShorts (JayWebtech) macOS (Apple Silicon and Intel), Windows, Linux (.deb, .rpm, AppImage); OpenShorts Runs in Docker; Linux and Windows (Docker Desktop with WSL2) are documented; macOS not mentioned
- Setup effort: AutoClip Easy, desktop installers (.dmg / -setup.exe) with Python and FFmpeg bundled; Docker or pip for CLI; AutoShorts (JayWebtech) Easy; unsigned installers from GitHub Releases plus FFmpeg on PATH; OpenShorts Medium, docker compose up --build, then enter API keys in the dashboard

Stars show popularity, not quality. Check each project page before publishing.

Want share images and a ready video description? Open a project's creator kit.

Numbers: GitHub, fetched nightly. Facts: read from each project's own documentation, with the source on its page. How we check. zhouxiaoka/autoclip ↗JayWebtech/autoshorts ↗mutonby/openshorts ↗

AutoClip vs AutoShorts (JayWebtech) vs OpenShorts

Stars over time

Notes for a video or post

Cookie preferences

Report a problem