Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Sport Vision
Public APIsIdentify sport, brands and gear in an image. Also does image sports captioning
-
geo-sleuth
SkillsAn 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.
git clone https://github.com/Oldcircle/geo-sleuth.git -
Rdp.Vision
MCP serversOrder and manage Windows RDP and Linux VPS servers paid with crypto: deploy, power, renew, top up.
-
CaPtain
Agents & frameworksCaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters
git clone https://github.com/waltstephen/CaPtain.git -
WeVisOne-VL-2B
Modelsimage text to text model by tencent · transformers
tencent/WeVisOne-VL-2B -
md-vision
MCP serversRead markdown with inlined images and index headings for agentic RAG workflows.
md-vision@0.2.1 -
neo-vision
MCP serversSpatial DOM maps for AI agent browser navigation with anti-bot stealth.
neo-vision@0.2.2 -
Cloud Vision API
Public APIsIntegrates Google Vision features, including image labeling, face, logo, and landmark detection, optical character recognition (OCR), and detection of explicit content, into applications.
-
VectorDB-Plugin
AI repositoriesProgram that lets you ask questions about your documents and audio or video files.
git clone https://github.com/BBC-Esq/VectorDB-Plugin.git -
d3-nano
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-nano -
XRay-Vision
MCP serversAI-powered codebase analysis — call graphs, security, dead code, complexity. 150+ tools.
-
cerul
Agents & frameworksOpen-source video processing core and CLI. Search and annotate local videos with your own model endpoints.
git clone https://github.com/cerul-ai/cerul.git -
video-vision-mcp
MCP serversAnalyze any video (local file or URL) into frames + transcript for Claude Code
video-vision-mcp@0.5.1 -
vllm-mlx
AI repositoriesHigh-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
git clone https://github.com/waybarrios/vllm-mlx.git -
Piranha Vision & DevTools
MCP serversBJJ video analysis — YOLO pose detection, AI technique analysis, and highlight reels.
-
d3-lite
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-lite -
Future Vision
PromptsWrite a compelling vision statement about where I see [project/work] going in the next 2-3 years and how sponsors can be part of that journey.
-
Cradle
AI repositoriesThe Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.
git clone https://github.com/BAAI-Agents/Cradle.git -
awesome-ai-tutorials
Docs & tutorialsThe best collection of AI tutorials to make you a boss of Data Science!
git clone https://github.com/FrancoisPorcher/awesome-ai-tutorials.git -
Moltline Vision Maths
MCP serversImage header probing, bbox conversion, resize plans and colour maths. 4 of 6 free.
-
VisionFlow Match
MCP serversHosted OpenCV for finding a pattern image inside a larger image: template matching, ORB/SIFT...
-
three.ws Vision
MCP serversImage understanding for AI agents — analyze and describe any image via the three.ws pipeline.
@three-ws/vision-mcp@0.1.2 -
macos-vision-mcp
MCP serversLocal OCR & screen understanding for agents: read any window, find what to click. No uploads.
macos-vision-mcp@0.7.0 -
VisualNews-Repository
Datasets & benchmarks[EMNLP'21] Visual News: Benchmark and Challenges in News Image Captioning
git clone https://github.com/FuxiaoLiu/VisualNews-Repository.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.