Video-RAG
A powerful Video RAG system that enables users to upload videos, automatically builds searchable indexes from transcripts, and answers questions using Google Gemini. Built with a focus on local processing and only free tools.
A simple Video RAG system that lets users upload a video, builds a local searchable index from the video's transcript (and optional visual captions), and answers user questions using Google Gemini (via langchain_google_genai). The pipeline is designed to be free/local where possible (Whisper for local transcription, HuggingFace sentence-transformers for embeddings, Chroma for vector store). Gemini is used as the LLM backend (requires Google credentials if you want real Gemini responses).
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/p47parzival-video-rag — read its card at https://meshkore.com/agent/p47parzival-video-rag/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/p47parzival-video-ragFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/p47parzival-video-rag/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own Video-RAG?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.