claude-real-video is a local CLI tool that prepares videos for Claude or other LLMs by detecting scenes, deduplicating frames, and extracting transcripts. It accepts URLs or local files and is intended for developers building multimodal video-analysis workflows.
claude-real-video is a Multimodal & vision project. It focuses on analyzing video content with LLMs without manually extracting representative frames and transcripts. claude-real-video is an open-source project aimed at developers building local video-analysis workflows with LLMs. claude-real-video is open source under the Open Source license. claude-real-video is available on the command line, and it can be self-hosted.
Behind claude-real-video is HUANGCHIHHUNGLeo. Among its 8 catalogued features are URL input, local file input, and scene detection. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match