AutoClip: local long-video-to-shorts tool by solo dev hits 8.8k GitHub stars
alex_verem · x · 2026-09-23
A recommended open-source project, AutoClip, by Shanghai solo developer zhouxiaoka, has reached 8.8k stars and 1.6k forks on GitHub (600 stars in one day).
- Workflow: feed it a long video, podcast, lecture, or stream; Whisper transcribes locally, the transcript is scored for clip-worthiness, then the best segments are cut with auto-generated titles and covers.
- Fully local option: scoring runs via Ollama or LM Studio, or cloud models (Gemini, Qwen, any OpenAI-compatible key)—only transcript text leaves the machine, never the footage.
- Features: direct YouTube link input, desktop apps (Mac/Windows), Docker, CLI, and publishing finished clips to 13 platforms including TikTok, Instagram, YouTube, X, and LinkedIn.
- Backstory: the developer's GitHub bio reads "I know nothing about code" and the second-biggest contributor is Cursor's coding agent; four releases shipped in four days, so expect rough edges.
Related event: AutoClip: Open-Source Local AI Video Clipper Hits 8,800 Stars(2 posts)→
More from coding & agent
- DeepLearning.AI launches free course on building on-device memory AI assistants with Qdrant — DeepLearningAI · 2026-09-23
- Hugging Face ships lerobot JS package to read robot datasets in the browser — mishig25 · 2026-09-23
- DavidKPiano: a coding agent's "2-3 days" estimate means days fixing its missed edge cases — DavidKPiano · 2026-09-23
- Sol 6 agent still autonomously running on a single goal after 21 hours — gregmushen · 2026-09-23
- Harvard, Andrew Ng and Karpathy Teach AI Engineering Free: A 9-Step Learning Path — mdancho84 · 2026-09-23
- Cookie banners vs agents: X user shows Europe's web friction makes AI agents look superhuman — jeff_weinstein · 2026-09-23