Item detail
github.com

HUANGCHIHHUNGLeo/claude-real-video

HUANGCHIHHUNGLeo/claude-real-video is an AI project that RepoRadar is tracking in its AI Agents section, currently rated Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 9.8 out of 10.

Score8.3
Popularity1.0
Riskconditional
TierGold
Score breakdown
Usefulness9.0
Novelty8.0
Momentum8.0
Maturity6.5
Open-source/build8.4
Evidence7.2
Workflow potential9.8
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for AI agent developers, video / media researchers, RAG teams, knowledge-base builders, content / e-learning creators, and accessibility engineers who need a local-first, scene-aware, deduplicated video frame + transcript pipeline that runs offline and exposes a Claude Code skill (`skills/claude-real-video/`) for drop-in install. It collapses a 10-minute static slide deck into 1 frame

Who should use it

AI agent developers and Claude Code users who want a local-first video-to-LLM bridge that ships as a skill (`skills/claude-real-video/`) for one-command install and that runs scene-change-aware frame extraction + sliding-window dedup + Whisper transcription locally on the user's own machine Video / media researchers, RAG teams, knowledge-base builders, and content / e-learning creators who need a tool that collapses a 10-minute static slide deck into 1 frame and catches every visual change in a fast-cut reel (vs fixed 1-fps sampling that misses frames between samples), with a `--why` flag that focuses the analysis on a stated goal (e.g. 'find the pricing strategy') Accessibility engineers, researchers, and analysts who need a local Whisper transcript + deduplicated frames folder they can paste into any LLM afterwards (Claude, ChatGPT, Gemini, or local), with the `--kb` flag that saves the result as a dated note in the user's own notes folder so it persists beyond a one-shot `crv-out/` Privacy-conscious teams that need the processing to stay on their own machine — only the frames / text the user chooses to paste into an LLM afterwards leaves the box, which is the right default for video material that may be under NDA or contain personal information

Who should skip it

Pass on HUANGCHIHHUNGLeo/claude-real-video if its scope or audience does not match what your team is building right now.

About this signal

HUANGCHIHHUNGLeo/claude-real-video is tracked by RepoRadar as an AI project in the AI Agents section. First seen 2026-07-03; the source record was last checked on 2026-07-03. The current verdict is 'try now' with a Gold tier and easy setup difficulty. Across RepoRadar's eight signals, HUANGCHIHHUNGLeo/claude-real-video is strongest on workflow potential (9.8) and practical usefulness (9.0) and weakest on maturity (6.5) — a profile worth weighing against your own priorities. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The HUANGCHIHHUNGLeo/claude-real-video record combines a 8.3/10 composite score with separate popularity (1.0), risk (conditional), and setup (easy) signals. See the scoring methodology for the current weights and evidence definitions.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

Requires ffmpeg, opencv-python-headless, scenedetect, yt-dlp on PATH and a Python 3.10+ environment; on Windows, the bundled `install.ps1` handles PATH setup, on macOS the bundled `install.sh` handles Homebrew ffmpeg install, and on Linux the dependency install is manual (`apt install ffmpeg` then `pip install claude-real-video[whisper]`). Review the README's `System requirement: ffmpeg` section before promoting to multi-user deployment; The `--why` / `--kb` flags save dated notes to the user's notes folder — review the note path and the `MANIFEST.txt` before sharing the saved note across a team, because the saved note inherits any PII / NDA-sensitive content from the source video. The processing itself runs locally and only the user-chosen frames / text leaves the box, which is the right default for sensitive material; Whisper transcription quality depends on the model size and the audio quality — for noisy audio or accented speech, the smaller models under-transcribe, and the larger models are slower. The README documents the `faster-whisper` backend and the model size trade-off; pick the model size per use case (tiny / base / small / medium / large-v3).

Evidence links
Closest alternatives / related signals
video-frame-extractor scene-change-detection sliding-window-dedup whisper-transcription local-first yt-dlp ffmpeg opencv
Verification record

What RepoRadar actually verified

Discovered

Automated discovery and source capture. Last checked 2026-08-13T20:20:15Z.

No editorial or hands-on review is claimed. This record remains at Discovered.

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

32 dated snapshots retained from 2026-07-04 through 2026-08-13; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score8.3 current · +0.0 net
Repository momentum9.3 current · +1.3 net
GitHub stars (observed)2,014 current · +441 net
GitHub stars2,014 exact observation
Versionv0.9.0
Last release2026-08-11T02:03:33Z
Maintenanceactive
Current riskconditional
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineClaude Code

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-138.39.32,014conditionaltry nowactive
2026-08-128.39.32,006conditionaltry nowactive
2026-08-118.39.31,996conditionaltry nowactive
2026-08-108.39.31,989conditionaltry nowactive
2026-08-098.39.31,982conditionaltry nowactive
2026-08-088.39.61,978conditionaltry nowactive
2026-08-078.39.61,926conditionaltry nowactive
2026-08-068.38.0Not recordedconditionaltry nownot recorded
2026-08-058.38.0Not recordedconditionaltry nownot recorded
2026-08-048.39.61,926conditionaltry nowactive
2026-08-038.39.61,926conditionaltry nowactive
2026-08-028.39.31,914conditionaltry nowactive

Why the record changed

stars changed

Stars changed: 2006 → 2014.

stars changed

Stars changed: 1996 → 2006.

version changed

Version changed: v0.7.16 → v0.9.0.

stars changed

Stars changed: 1989 → 1996.

stars changed

Stars changed: 1982 → 1989.

stars changed

Stars changed: 1978 → 1982.

stars changed

Stars changed: 1926 → 1978.

stars changed

Stars changed: 1914 → 1926.

stars changed

Stars changed: 1910 → 1914.

stars changed

Source-observed stars changed: 1908 → 1910. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Stars changed: 1875 → 1895.

version changed

Version changed: v0.7.15 → v0.7.16.