搜索「Vision」的结果

co.instavision/instagram-discovery

Find Instagram creators and leads by niche, city, follower range or lookalike accounts.

io.github.simonmak-ascent/vision-driven-design

Spec-driven development MCP server: 8 phases, bi-directional traceability, 7 quality gates.

io.github.patrickchugh/terravision

Cloud architecture diagrams with official AWS, Azure and GCP icons, from Terraform or a JSON graph.

io.github.eralpozcan/vision-squeezer

通过将图像对齐到分块边界来削减视觉 LLM 的 token 成本——支持 Claude、GPT、Gemini、Llama、Qwen

io.github.A9T9/uivision-mcp

MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input

io.github.AgewellEPM/isolated-tester

Isolated macOS app tests, MCP images, OCR/ASCII frames, accessibility and evidence reports.

io.github.AgewellEPM/tinkyvision

Screen observation, OCR and permission-controlled app input over MCP for Apple silicon Macs.

io.github.woladi/macos-vision-mcp

为 Agent 提供本地 OCR 与屏幕理解：读取任意窗口、找出该点哪里，数据不外传。

io.github.q1023884985/visiongemma

Local AI vision MCP server for Windows: OCR, chart analysis, scene description. 100% offline.

io.github.xlight/deepseek-visionary

DeepSeek web vision model as an MCP server with browser auto-login.

io.github.KitDevUA/video-vision-mcp

把任意视频（本地文件或 URL）解析成关键帧与文字稿，供 Claude Code 使用。

io.github.VOYAGER-Inc/excel-vision-mcp

Excel MCP with image extraction and write support — AI agents see and edit xlsx files

io.github.nirholas/vision-mcp

面向 AI 代理的图像理解——经 three.ws 管线分析并描述任意图像。

io.github.Braynexservices/nigeria-admin-divisions

Nigeria's 36 states + FCT and 774 LGAs — list states, get LGAs. Fully offline, no key.

io.github.japlete/md-vision

读取把图片内联后的 Markdown 并生成标题索引，服务于智能体 RAG 流程。

io.github.pachote/nira-screen-vision

为 Claude 提供实时屏幕捕捉 + AI 视觉——看见、分析并 OCR 你的屏幕。

io.github.matthewalexong/neo-vision

为 AI 智能体的浏览器导航提供空间化 DOM 地图，并具备反机器人隐身能力。

io.github.totte-dev/vibe-provision

从 YAML 开通 SaaS 服务并注入 .env，支持 Clerk、Stripe、Resend 等。

io.github.fonkychen/nature-vision-mcp

识别生物物种，返回拉丁学名及置信度评分。

io.github.isamu/mulmocast-vision

简单而时尚的演示幻灯片生成器。

io.github.putervision/world-model-mcp

Persistent 3D/2D spatial world model for AI agents with dynamic velocity and entity tracking.

io.github.putervision/vision-memory-mcp

Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.

io.github.putervision/state-memory-mcp

Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.

io.github.putervision/behavior-mcp

In-browser ~60Hz behavior tree execution engine with reactive triggers and blackboard projection.