Image Understanding
Describing and detecting objects in images. As of 2026-11-21, 43 indexed products offer it (20 with full profiles), in 7 forms: 31 MCP servers, 3 Infrastructure, 3 Plugins, 2 Agent skills. 11 were published in the last 90 days, against 12 in the 90 days before. ai-engineering-from-scratch has the most GitHub stars, 66% of the total across 38 products with their own repository.
CapabilitySegment label: Lagging the catalogue DER
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 31 indexed · 8 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | video-search-and-summarizationNVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs. | NVIDIA-AI-Blueprints | 2.0k | today | ||
| 2 | watch-skillWatch video and live sessions, keep timestamped evidence, and verify an agent's own work. | oxbshw | 597 | 5d ago | ||
| 3 | imagesorcery-mcpAn MCP server providing tools for image processing operations | sunriseapps | 339 | 6mo ago | ||
| 4 | nuphus-mcpDesktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio). Not a DSH plugin — DSH users install dsh-nuphus-mcp. | mrpulor-gh | 335 | 9d ago | ||
| 5 | Visual Memory MCPLocal visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding. | putervision | 40 | 1mo ago | ||
| 6 | fiftyone-mcp-serverControl FiftyOne computer vision datasets through AI assistants using 80+ operators. | AdonaiVera | 27 | 2d ago | ||
| 7 | omni-lprAn MCP server for automatic license plate recognition | habedi | 27 | 19d ago | ||
| 8 | pardesline3D vision and medical imaging: 43 datasets with licences, 73 algorithms on clouds, meshes, CT/MRI | pardesline | 10 | 4d ago |
Infrastructure 3 indexed · 3 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | deeplakeDeeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training. | activeloopai | 9.3k | 6mo ago | ||
| 2 | bootcampDealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc. | milvus-io | 2.5k | 1mo ago | ||
| 3 | Multi-Agent-Medical-Assistant⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients. | souvikmajumder26 | 1.0k | 1y ago |
Plugins 3 indexed · 3 profiled
3 of these are Claude plugins, which Claude Code documents (protocol-level). DER
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | sam3-segmentationAgent skill: outline, mask and count objects in photos with Meta's SAM 3 on your own NVIDIA GPU, with review, exports and a viewer. Works with Claude Code, Codex, Cursor, Pi and other Agent Skills clients. | lillyguisnet | 147 | 28d ago | ||
| 2 | fiftyoneBuild high-quality datasets and computer vision models. Visualize datasets, analyze models, find duplicates, run inference, evaluate predictions, and develop custom plugins. | voxel51 | 48 | 1d ago | ||
| 3 | ai-engineerUse this agent when implementing AI/ML features, integrating language models, building recommendation systems, or adding intelligent automation to applications. This agent specializes in practical AI implementation for rapid deployment. Examples:\n\n<example>\nContext: Adding AI features to an app\nuser: "We need AI-powered content recommendations"\nassistant: "I'll implement a smart recommendation engine. Let me use the ai-engineer agent to build an ML pipeline that learns from user behavior."\n<commentary>\nRecommendation systems require careful ML implementation and continuous learning capabilities.\n</commentary>\n</example>\n\n<example>\nContext: Integrating language models\nuser: "Add an AI chatbot to help users navigate our app"\nassistant: "I'll integrate a conversational AI assistant. Let me use the ai-engineer agent to implement proper prompt engineering and response handling."\n<commentary>\nLLM integration requires expertise in prompt design, token management, and response streaming.\n</commentary>\n</example>\n\n<example>\nContext: Implementing computer vision features\nuser: "Users should be able to search products by taking a photo"\nassistant: "I'll implement visual | ccplugins | — | 3mo ago |
Agent skills 2 indexed · 2 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | geo-sleuthAn agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot. | Oldcircle | 7.4k | 2d ago | ||
| 2 | dsh-vision-toolkit[dsh]为纯文本模型设计更强大的视觉工具箱:一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI. | Anionex | 949 | today |
Frameworks 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | OpenCOOD[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V. | DerrickXuNu | 841 | 2y ago | ||
| 2 | AAAI-2024-PapersAAAI 2024 Papers: Explore a comprehensive collection of innovative research papers presented at one of the premier artificial intelligence conferences. Seamlessly integrate code implementations for better understanding. ⭐ experience the forefront of progress in artificial intelligence with this repository! | DmitryRyumin | 589 | 1y ago |
Agent projects 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | ai-engineering-from-scratchLearn AI Engineering! Learn it. Build it. Ship it for others. | rohitg00 | 80k | 3d ago |
Libraries 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | UnstructuredLibrary and hosted platform for partitioning PDFs, Office files, HTML and images into structured elements and chunks for RAG pipelines. | Unstructured | 16k | 1d ago |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 31 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 2 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Claude Code | 2 |
| Cursor | 2 |
| Codex | 2 |
| Gemini CLI | 1 |
| GitHub Copilot | 1 |
| OpenCode | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| GitHub | 1 | 2.3% |
| PostgreSQL | 1 | 2.3% |
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| image analysis | 2 |
| image recognition | 5 |
| computer vision | 31 |
| object detection | 3 |
| image captioning | 0 |
| vision model | 2 |
Segment statistics
Whole catalogue (43 indexed products). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized among capabilities, with launches growing more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.457 means stars are spread as if across about 2 equally popular projects — highly concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .