vlm-run/mm

Ever needed to take 8000 PDFs, 2000 videos, and 500 spreadsheets and feed them to an LLM as a knowledge base? Well, mmore is here to help you! mmore is a scalable multimodal pipeline for processing, indexing, and querying multimodal documents

Make any agent harness multimodal-native.

Get clean data from tricky documents, powered by vision-language models ⚡

SmartRAG is a privacy-first multimodal RAG system that lets you chat intelligently with your documents, images, and audio. Upload PDFs, Word files, or recordings and get accurate, context-aware answers all processed locally on your device with no external APIs.

A multimodal video memory for humans and AI agents

Program that lets you ask questions about your documents and audio or video files.

Intelligent File Searcher that can search for descriptions in media files like photos, for example "receipt from market of $42.00" using AI based classification

Open Visual Agentic Intelligence

ds-vision-skill: Vision skill suite to add multimodal image capabilities for DeepSeek, and other text-only models as well.