# SamuelZ12/longcut

The best way to learn from long videos

Repository: https://github.com/SamuelZ12/longcut
Canonical: https://ross.abutalabs.com/products/longcut
Homepage: https://www.longcut.ai
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Last push: 2026-06-04T15:34:56+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 85, release rhythm 35, longevity 26
- inputs: {"age_days": 372, "days_push": 90, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1183, forks 215 (observed 2026-08-28T04:03:54.489732+00:00)

## What it is
LongCut is a Next.js web application that turns long-form YouTube videos into a structured learning workspace with AI-generated highlight reels, timestamped transcript-grounded chat, and a personal notes dashboard. It uses multiple LLM provider adapters (MiniMax, Grok, Gemini), YouTube transcript extraction, and Supabase for auth, persistence, and rate limiting.

## Use cases
- summarize hour-long youtube videos quickly
- chat with a video transcript and get timestamp citations
- generate highlight reels from long lectures
- take and review notes across multiple videos
- extract youtube transcripts for free
- ask questions about a video and jump to the answer moment

## When to choose
- you want to learn from long YouTube videos without watching them in full
- you need timestamped, transcript-grounded Q&A over video content
- you want a self-hostable AI video study tool with notes and history

## When to avoid
- you need to process videos outside of YouTube
- you need offline or local-only processing without LLM API keys
- you need to analyze private or caption-less videos

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, rag, chatbot, web-framework, auth, caching, rate-limiting, security
- domain: artificial-intelligence, large-language-models, education, web-development
- platform: self-hosted, cloud
- tags: youtube, video-learning, transcript, nextjs, supabase, summarization, highlight-reel, ai-notes, video, natural-language-processing, web-server, nodejs

## Member repositories
- SamuelZ12/longcut (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:54.489732+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 2026-08-30T06:24:31.182441+00:00, confidence not recorded.
  - readme: https://github.com/SamuelZ12/longcut (fetched 2026-08-28T04:03:54.489732+00:00, sha a07da6eb4a4c)
  - homepage: https://www.longcut.ai (fetched 2026-08-29T12:31:25.634066+00:00, sha e4d820ffa73b)
- Data as of 2026-08-30T08:39:29.467469+00:00.