# KnowClip-ai/knowclip > The open-source core of KnowClip: a Tauri 2 + React + Python FastAPI desktop app that finds highlight moments in long videos (lectures, streams, podcasts) using local Paraformer ASR and an LLM, then exports clips fast via ffmpeg. Published as a learning reference for the full pipeline. - Magnitude: 1.3 out of 10 — Steady - Stars: 227 total · +1 star on 2026-09-29 (UTC), ≈ 6 by evening - Star trust: star growth looks organic - Category: Apps · Language: TypeScript · License: AGPL-3.0 · Created: 2026-09-13 · Last push: 2026-09-14 - GitHub: https://github.com/KnowClip-ai/knowclip · Page: https://gitnova.dev/en/r/KnowClip-ai/knowclip ## Useful for - Cut clips from a stream recording without uploading the video to third-party services - Study the local ASR → LLM → ffmpeg pipeline architecture from the open-source code - Batch-export dozens of short segments from a multi-hour lecture ## Why it’s here - 1 star so far today, about 6 expected by the end of the day. - The repository is 16 days old and already has 227 stars. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 6 - Issues and pull requests: 1 - Watchers: 1 - Average over the last week: 17 per day - Usual pace: 7 per day ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-04 … 2026-11-02: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 12 days 09-18 1.9, 09-19 1.4, 09-20 1.5, 09-21 1.5, 09-22 1.5, 09-23 1.4, 09-24 1.9, 09-25 2.0, 09-26 2.3, 09-27 2.0, 09-28 1.6, 09-29 1.4 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-09-29 09:11 UTC, updated every 30 minutes.