Havuz

PixelRAG, web sayfaları ve belgeleri screenshot tile’larına dönüştürüp görsel içerik üzerinden arayan bir RAG sistemi sunuyor.

Neden yükseliyor · 121 günde 10.101 yıldıza ulaşması ve 8,28 milyon Wikipedia sayfasını içeren canlı indeks/API sunması dikkat çekiyor. README, Berkeley SkyLab, BAIR ve Berkeley NLP bağlantılı araştırma çalışmasını resmi kod tabanı olarak tanımlıyor. Son 28 günde 5 commit ve 4 farklı yazar görünmesi katkı çeşitliliğine işaret etse de aktiviteyi çok yüksek göstermiyor.

为 Claude Code 赋能多模态视觉能力，适配 纯文本 LLM 底座，用于截图 / UI / 图表分析；搭配 browser-harness 可做前端布局自动化检查。

让 AI 实时看见你的屏幕：按变化量筛选帧、多帧拼进一张图，静止画面几乎不花 token

Cut your Claude bill 59–70% by rendering bulky LLM context as dense PNG pages — 100% read accuracy, exact per-provider billing math (Anthrop

The vision plugin for OpenCode that truly understands images. Inspect, read, and reason about any screenshot or picture with deeper understa

FlowVision，一键分析项目代码 · 自动生成架构流程图 · 可视化编辑 · MCP 实时同步

Transparent proxy for Claude Code that auto-routes image-bearing requests to a multimodal model — so a non-multimodal primary model never cr

给 DeepSeek 装上眼睛 — MCP Server + 通义千问VL, 剪贴板图片→视觉模型→文字描述 / Give DeepSeek the ability to see images via clipboard + Qwen-VL

On-device subject cutouts, image labels, and OCR for React Native. Apple Vision (iOS) · Google ML Kit (Android). Built with Nitro Modules.

给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH 插件）。

Design-fidelity QA for DeepSeek Harness: lend any text-only model an eye, then judge whether the implementation matches the mock. Ships the

OpenCode vision support: automatically saves pasted images and guides non-vision models to recognize them via tool calling. Supports single

A free, open-source tool that lets you use DeepSeek in your favorite apps and coding tools without paying for API access or subscriptions.

🚀 让不支持视觉的大模型获得真·图片理解能力: 零安装、不破解PoW、OpenCV自动过登录验证码、用后即删的 DeepSeek C端识图模式 CLI

Build world models from scratch — from perception and latent dynamics to planning, JEPA, VLA, and 3D/4D intelligence.

🐳 whalegate — OpenAI-compatible gateway into DeepSeek web sessions (Rust): account pool, failover, SSE, native-style tool calling (tool_choi

Search knowledge by what documents mean and how they look — not one or the other.

neural networks in pure C

让非多模态模型（DeepSeek 等）把图片识别委托给任意 OpenAI 兼容的多模态模型。零厂商硬编码，主模型支持视觉时自动隐藏自己。

Use your X Premium or SuperGrok subscription in pi.

Give text based LLMs in Claude Code working eyes using a local Ollama vision model. Screen capture, clipboard reading, and image file analys

Claude Code + DeepSeek 等纯文本模型使用时，无法理解图片内容——截图里的报错、UI 设计稿、手绘架构图、文档扫描件，模型统统"看不见"，通过 mcp vision 让模型拥有眼睛。

Agent-native screenshot gallery CLI: index, caption, search & safely rename local photos.

Free image reading & generation for DeepSeek Harness (rc.7 / rc.8 / v0.1.1-rc.1 / rc.2 / v0.1.2-alpha.3) — paste-image reading with auto vis

Native face detection, tracking, head pose, guidance, auto capture and liveness for React Native and Expo. Google ML Kit on Android, Apple V

A vision backend for AI Agents — self-healing Claude Code Agent Skill. Routes images to Mimo/OpenAI/Ollama vision API.

ComfyUI nodes for Strata: text, structured prompts, vision and managed local inference with GPU handoff. Publisher: t8star.

A ComfyUI diffusers implementation of Krea2 for the highest possible quality and most options

Local-first visual media plugin for DeepSeek Harness: local video preprocessing, native vision, copyable image history, and video playback.

上传表情包 → AI 自动写描述 → 聊天机器人按场景自己挑着发（含双向发送 / 多端渲染 / 踩坑思路）

Visual bridge for text-only models and visual enhancement toolkit for multimodal AI agents — OCR, zoom, PDF/Office rendering, web vision and

为 DeepSeek V4.0 等单模态大模型装上眼睛和耳朵 —— 本地视觉+音频 MCP 服务器，基于 Ollama + MiniCPM-V 4.6 + faster-whisper，图片描述·视频分析·语音转文字

Codex Skill：让纯文本模型（DeepSeek）借助 StepFun step-3.7-flash 获得看图能力 | Give text-only Codex models (DeepSeek) image understanding via StepFun step-3

Convert local documents (PDF, DOCX, PPTX, images, TXT, Markdown) to clean Markdown with optional LLM vision — Python SDK

Capability-aware vision + paste extension for the pi coding agent. Delegates image analysis only when the active model is text-only; passes

Give non-multimodal Claude Code main models the ability to see pasted screenshots — a ~200-line UserPromptSubmit hook.

Aster describes what a lecture video shows but never says, so blind and low-vision students can follow it

Smart hands for your AI agents — write-capable, multi-plane (KVM + BMC + SSH) MCP server for bare-metal control (PiKVM/GLKVM, Redfish/IPMI B

MCP server that gives text-only LLM coding agents vision — analyze images via any multimodal model (mimo, Claude, Gemini, OpenAI-compatible)

一个工具 = MiniMax 全部多模态能力：DSH 纯文本模型看图/画图/生视频/说话/唱歌/翻唱/搜索/查额度 | One mmx_bridge tool = all MiniMax multimodal (VLM/image/video/speech/music/cover

Model-agnostic AI poster grid inspector: detect a poster's layout grid system with a vision model, view it overlaid, and export SVG guides /