Fetches YouTube transcripts and enables semantic search within them using local embeddings, allowing an LLM to retrieve relevant passages with timestamps.
Analyze an hour-long YouTube video sentence by sentence in three minutes, and extract the information you need from the screen. Open-source local MCP server for AI clients.
Indexes YouTube channel transcripts and exposes semantic search and excerpt retrieval to MCP clients, returning cited fragments with timestamps and video links. Supports channel/date filtering and subtitle-first transcription with Whisper fallback.
Enables semantic code search across codebases with automatic incremental indexing. Searches return relevant code snippets with file paths and line numbers based on natural language queries.