#multimodal

Turn documents into AI-ready Markdown with visual understanding

Verifiable handwriting synthesis for failure-driven multimodal training and regression.

MCP server that gives text-only LLM coding agents vision — analyze images via any multimodal model (mimo, Claude, Gemini, OpenAI-compatible). Works with Claude Code, Codex, Kimi, opencode, PI.

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

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.

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 + 26 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

给纯文本大模型装上原生视觉：流式真实思考链 · 跨轮次无感重看 · 像素级证据与 SVG 图元 · OpenAI/Anthropic/Responses 三协议兼容 | Native vision for text-only LLMs: streaming real thinking chain, cross-turn re-view, pixel-level evidence & SVG primitives, OpenAI/Anthropic/Responses compatible.

Your self-hosted AI workspace, powered by Pi Coding Agent. Code, manage files, and create images, video & audio from desktop, tablet or phone. Deploy on Linux, macOS or Windows. 自托管 AI 工作台：原生会话、文件与任务管理、多媒体创作，电脑/平板/手机随时使用。

🎬 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)

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

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

Codex companion for WeChat public search: a four-route crawler cascade captures complete text, tables and images, then extracts visual knowledge. Not affiliated with OpenAI.

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

DeepSeek Harness 图像理解插件 · 8 种分析模式 · 支持任意API接口 · 内置免费视觉模型 | DeepSeek Harness vision plugin · 8 analysis modes · works with any OpenAI- or Anthropic-compatible API · built-in free vision model

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.

Privacy-first local Ollama chat with expert personas, reasoning, multimodal input, context-aware history, and long-term conversation memory.

Sam 1.0 (Codename: Astra) — multimodal general-purpose AI by Sam AI Labs. Model card, demo chatbot & official website.

🔍 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

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

Discord AI friend that talks like a real person instead of a chatbot. Long-term memory, mood tracking, voice notes, and proactive DMs.

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.