Local LLM
Jan
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer
★ 44.8k starsCustom (check repo)
View guide →// local-llm · HUANGCHIHHUNGLeo/claude-real-video
claude-real-video
claude-real-video is an open-source local llm project by HUANGCHIHHUNGLeo (HUANGCHIHHUNGLeo/claude-real-video on GitHub). It has 2,196 GitHub stars and 195 forks, is released under the MIT license, and was last updated on GitHub on 1 October 2026.
Let any LLM actually watch a video — frames plus transcript, run locally.
💎 Hidden gem★ 2.2k stars⑂ 195 forksMITupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- HUANGCHIHHUNGLeo/claude-real-video
- GitHub stars
- 2,196
- Forks
- 195
- License
- MIT
- Last updated on GitHub
- 1 October 2026
- Category
- Local LLM
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Install the tool
Set it up from the repo.
- Give it a video
Pass a URL or local file.
- Extract
It pulls scene-aware frames and the transcript.
- Ask the LLM
Query any model about the video content.
// features
Why people love it
Scene-aware frames
Extracts frames that represent scene changes.
Deduplication
Drops redundant frames to save context.
Transcript pairing
Combines visuals with spoken content.
URL or local
Works with online and offline video.
Any LLM
Not tied to Claude despite the name.
Runs locally
Processing happens on your machine.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/HUANGCHIHHUNGLeo/claude-real-video.git cd claude-real-video - Step 2 — Check the README
Every project documents its own setup; start with install requirements.
cat README.md | head -60 - Step 3 — Run it
Follow the project's launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch command
// use cases
What you can build
- Let LLMs summarize videos.
- Build video Q&A features.
- Analyze video content locally.
- Extract key moments from footage.
Advertisement
// faq
Questions, answered
Does it only work with Claude?
No, any LLM can consume the frames and transcript output.
Is claude-real-video free for commercial use?
MIT licensed — commercial use allowed.
How long a video can it handle?
Deduplication keeps context manageable; very long videos need chunking.
Does it need ffmpeg?
Yes, ffmpeg handles the frame extraction.
Is there a hosted pro version?
The site mentions a pro offering; the repo itself is open source.
// keep exploring
Similar tools
Local LLM
lobehub
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
★ 83.0k starsCustom
View guide →AI Chat
NextChat
✨ Zero-config AI chat assistant. No API key needed — sign up and instantly chat with GPT-5, Claude 4, Gemini 2.5, DeepSeek & 100+ top models. Pay-as-you-go s…
★ 88.8k starsMIT
View guide →Local LLM
meridian
Local API bridge to run Claude and Antigravity inside other coding clients.
★ 2.1k starsCustom
View guide →Local LLM
velorn
AI-native video editing on real timelines with local agents.
★ 497 starsGPL-3.0
View guide →Local LLM
airllm
Run a 70B LLM on a single 4GB GPU — layer-by-layer inference with almost no memory tricks skipped
★ 35.5k starsApache-2.0
View guide →// alternatives
Alternatives in Local LLM
The most-starred other Local LLM projects in the LibreAI catalogue — the realistic shortlist if claude-real-video is not the right fit.
- Ollama★ 182.1k
The simplest way to run open language models on your own machine.
- Open Webui★ 153.9k
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
- llama.cpp★ 130.2k
LLM inference in C/C++
- vLLM★ 93.1k
A high-throughput and memory-efficient inference and serving engine for LLMs
- lobehub★ 83.0k
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
// more in local-llm
More in Local LLM
Nearby Local LLM projects in the catalogue, closest in stars to claude-real-video — keep exploring the shelf either side of it.
- kalosm★ 2.2k
Run controllable pre-trained AI models locally, written in Rust.
- node-llama-cpp★ 2.2k
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
- WhisperJAV★ 2.3k
Noise-robust subtitle generator powered by Whisper and local ASR models.
- Orkas★ 2.2k
Local-first desktop where a commander LLM directs specialist coding agents.
- webclaw★ 2.4k
Fast Rust scraper that turns web pages into clean data for LLMs.
- agent-safehouse★ 2.1k
Sandbox for local AI agents so they only touch what they need.
Get claude-real-video
Free and open — grab the source, star the repo, and start creating.