#multimodal

Turn documents into AI-ready Markdown with visual understanding

DeepSeek Harness plugin: describe_image — give a text-only model vision through an OpenAI-compatible VLM endpoint

A full-stack multimodal meeting intelligence system with layered RAG, long-term memory, and skill-based generation.

On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Offline semantic search for everything on your disk - documents, code, PDFs, scanned images (OCR), video by the second. 100% local AI: hybrid RAG with keyword + vector + rerank, no API key, no cloud. Desktop app + 24 MCP tools for Claude Code, plus a multi-engine web researcher that quotes sources verbatim. 本地离线多模态语义检索

DSH DevKit: multimodal gallery + multi-agent supervision console (DeepSeek Harness dynamic Cordis plugin)

Eyes for text-only DeepSeek on DeepSeek Harness: model-invokable vision tool + wrapper adapters + general VLM channels (OpenAI-compatible / Gemini / local Ollama)

🎬 A powerful multimodal AI video summarizer. Supports YouTube/Bilibili/Local videos, smart frame extraction, Whisper transcription, and generates structured summaries via OpenAI/Qwen/Claude. (AI 视频摘要提取神器)

Multimodal RAG + Agentic AI research paper analyser — summarisation, vision figure analysis, grounded Q&A, and 4-source literature comparison. Built with LangGraph, FAISS and Groq.

Give Claude Code image understanding when its primary model cannot see images. Supports UI screenshots, photos, documents, charts, comparisons, and Windows clipboard input through Qwen.

🔍 100%-offline-capable multimodal semantic search for macOS. Find your files by meaning, not name — text, code, PDFs, images, audio. Ollama + Qwen3-VL local, Gemini/OpenAI optional. Power-user tool, macOS-only.

Gaze + voice as a multimodal input layer — look, speak, and your gaze-resolved intent goes to Claude.

LocalSight · 198M-A64M 思考型 MoE LLM，2×RTX4090 从零训练（pretrain→SFT→SimPO→RLAIF→Agent RL），GGUF/Ollama 可运行

Eyes for text-only DeepSeek: view_image tool (local Ollama or any OpenAI-compatible VLM) + chat image-attachment bridge — paste/drop images in the chat and the model can see them.

屏幕区域 OCR + 大模型自动答题助手 | Screen-region OCR + LLM quiz solver — 框住题目区域，内容一变自动截图、本地 OCR、大模型作答。支持 DeepSeek 等 OpenAI 兼容接口与多模态视觉模型

Provider-agnostic VLM query flow: one Agent that dispatches to OpenAI / Anthropic / Gemini / vLLM / Claude Code CLI / local HuggingFace model backends, returning parsed answers. Used by 3D-CoT.

Image understanding for the DeepSeek Harness — analyze_image tool with 8 modes, any OpenAI/Anthropic-compatible vision endpoint