# zhouxiaoka/autoclip

AutoClip : AI-powered video clipping and highlight generation · 一款智能高光提取与剪辑的二创工具

Repository: https://github.com/zhouxiaoka/autoclip
Canonical: https://ross.abutalabs.com/products/autoclip
Homepage: https://zhouxiaoka.github.io/autoclip_intro/
Language: Python
License: MIT
License Family: permissive
Topics: ai, ai-agents, ai-tools, ai-video, ai-video-editor, auto, auto-highlight, highlight, llm, video, video-editing, video-processing, videos
Last push: 2026-06-03T12:23:37+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 85, release rhythm 63, longevity 30
- inputs: {"age_days": 421, "days_push": 91, "days_rel": 91, "gap_med": 130.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7019, forks 1361 (observed 2026-08-28T04:09:53.332875+00:00)

## What it is
AutoClip is a self-hosted AI-powered video clipping system that downloads videos from YouTube and Bilibili, uses LLM-based content analysis to detect highlight moments, and automatically cuts them into clips with generated titles and smart collections. It uses a FastAPI + Celery + Redis backend with a React/TypeScript web interface and Docker deployment.

## Use cases
- automatically extract highlight clips from long videos
- clip livestream replays into short highlights
- generate clips from YouTube or Bilibili videos
- slice course videos into knowledge-point segments
- auto-generate titles for video clips
- organize clips into smart collections

## When to choose
- you want fully automated AI highlight extraction from long-form video
- you need a self-hosted pipeline with async processing and a web UI
- you create derivative content for YouTube/Bilibili and want clipping automated

## When to avoid
- you need fine-grained manual video editing with a timeline editor
- you require guaranteed frame-accurate professional editing output
- you don't want to run Docker/Redis or depend on third-party LLM APIs

## Facets
- artifact type: application
- maturity: active
- function: video-processing, machine-learning, llm-inference, web-framework, streaming, workflow-automation
- domain: artificial-intelligence, media, web-development
- platform: windows, python, self-hosted
- tags: video-clipping, highlight-detection, yt-dlp, celery, fastapi, react, subtitle-analysis, content-creation, bilibili, youtube-downloader, video, automation, docker, web-server, linux, macos, nodejs

## Member repositories
- zhouxiaoka/autoclip (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:53.332875+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:40:38.311815+00:00, confidence not recorded.
  - readme: https://github.com/zhouxiaoka/autoclip (fetched 2026-08-28T04:09:53.332875+00:00, sha 930ad92c9efb)
  - homepage: https://zhouxiaoka.github.io/autoclip_intro/ (fetched 2026-08-29T08:36:28.466496+00:00, sha 43642f8aac04)
- Data as of 2026-08-30T08:39:29.467469+00:00.