Lets any LLM agent actually watch videos: a watch_video tool takes a URL or local file and returns scene-aware keyframes fused with a timestamped transcript, processed 100% locally with per-source caching.
Enables search across videos you've watched via transcripts, on-screen text, and frames, citing exact timestamps. Point it at videos, channels, or playlists; it indexes everything locally and answers queries with deep links to the exact second.
Self-hosted video intelligence pipeline that turns video into structured, citable, queryable JSON scene graphs, enabling AI assistants to analyze and search across video libraries without re-processing.
Video player for humans and AI. GUI + CLI + a built-in MCP server (39 tools) to drive playback, clip, transcribe, and search your media library from Claude, Cursor, or any MCP client. Local Whisper subtitles. MIT, local-first.
Enables AI agents to query local video timelines by extracting speech, frame captions, and on-screen text into a SQLite store, exposing search and retrieval tools via MCP.
