InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. VectorDB-Plugin

    AI repositories

    Program that lets you ask questions about your documents and audio or video files.

    Stale GitHub, BBC-Esq 371 ★Updated 25 days ago

    git clone https://github.com/BBC-Esq/VectorDB-Plugin.git
  2. Cloud Vision API

    Public APIs

    Integrates Google Vision features, including image labeling, face, logo, and landmark detection, optical character recognition (OCR), and detection of explicit content, into applications.

    Indexed APIs.guru OpenAPI Directory, Google Updated 3 years ago

  3. d3-nano

    Models

    zero shot classification model by vllm-sr · transformers

    Stale Hugging Face Hub, vllm-sr 35 ♥apache-2.0Updated 31 days ago

    vllm-sr/d3-nano
  4. XRay-Vision

    MCP servers

    AI-powered codebase analysis — call graphs, security, dead code, complexity. 150+ tools.

    Stale Official MCP Registry, com.emtailabs Updated 8 months ago 1 note

  5. cerul

    Agents & frameworks

    Open-source video processing core and CLI. Search and annotate local videos with your own model endpoints.

    Stale GitHub, cerul-ai 164 ★Apache-2.0Updated 30 days ago

    git clone https://github.com/cerul-ai/cerul.git
  6. vllm-mlx

    AI repositories

    High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

    Stale GitHub, waybarrios 1,646 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/waybarrios/vllm-mlx.git
  7. video-vision-mcp

    MCP servers

    Analyze any video (local file or URL) into frames + transcript for Claude Code

    Stale Official MCP Registry, io.github.KitDevUA Updated 3 months ago 2 notes

    video-vision-mcp@0.5.1
  8. d3-lite

    Models

    zero shot classification model by vllm-sr · transformers

    Stale Hugging Face Hub, vllm-sr 29 ♥apache-2.0Updated 31 days ago

    vllm-sr/d3-lite
  9. BJJ video analysis — YOLO pose detection, AI technique analysis, and highlight reels.

    Stale Official MCP Registry, io.github.albermm Updated 8 months ago 1 note

  10. Cradle

    AI repositories

    The 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.

    Stale GitHub, BAAI-Agents 2,594 ★MITUpdated 2 years ago

    git clone https://github.com/BAAI-Agents/Cradle.git
  11. Future Vision

    Prompts

    Write 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.

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  12. awesome-ai-tutorials

    Docs & tutorials

    The best collection of AI tutorials to make you a boss of Data Science!

    Stale GitHub, FrancoisPorcher 124 ★Updated 16 months ago

    git clone https://github.com/FrancoisPorcher/awesome-ai-tutorials.git
  13. Moltline Vision Maths

    MCP servers

    Image header probing, bbox conversion, resize plans and colour maths. 4 of 6 free.

    Stale Official MCP Registry, com.moltlinestudio Updated 2 months ago 1 note

  14. VisionFlow Match

    MCP servers

    Hosted OpenCV for finding a pattern image inside a larger image: template matching, ORB/SIFT...

    Stale Official MCP Registry, com.saastemly Updated 45 days ago 1 note

  15. three.ws Vision

    MCP servers

    Image understanding for AI agents — analyze and describe any image via the three.ws pipeline.

    Stale Official MCP Registry, io.github.nirholas Updated 38 days ago 1 note

    @three-ws/vision-mcp@0.1.2
  16. macos-vision-mcp

    MCP servers

    Local OCR & screen understanding for agents: read any window, find what to click. No uploads.

    Stale Official MCP Registry, io.github.woladi Updated 2 months ago 1 note

    macos-vision-mcp@0.7.0
  17. VisualNews-Repository

    Datasets & benchmarks

    [EMNLP'21] Visual News: Benchmark and Challenges in News Image Captioning

    Stale GitHub, FuxiaoLiu 106 ★Updated 2 years ago

    git clone https://github.com/FuxiaoLiu/VisualNews-Repository.git
  18. excel-vision-mcp

    MCP servers

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

    Stale Official MCP Registry, io.github.VOYAGER-Inc Updated 3 months ago 1 note

    excel-vision-mcp@1.2.1
  19. model by lightx2v · minimax-h3

    Stale Hugging Face Hub, lightx2v 92 ♥Updated 19 days ago

    lightx2v/MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VA
  20. Analyze images from multiple angles to extract detailed insights or quick summaries. Describe visu…

    Stale Official MCP Registry, ai.smithery Updated 13 months ago 1 note

  21. image text to text model by LiquidAI · gguf

    Stale Hugging Face Hub, LiquidAI 43 ♥otherUpdated 41 days ago

    LiquidAI/d1-omni-600M-GGUF
  22. Spec-driven development MCP server: 8 phases, bi-directional traceability, 7 quality gates.

    Stale Official MCP Registry, com.ascent-partners Updated 34 days ago 2 notes

    @simonmak-ascent/mcp@1.9.4
  23. Saudi and regional energy data: registers, series, trackers, briefs; atlas layers need a member key.

    Stale Official MCP Registry, sa.com.renewablevision Updated 7 days ago 1 note

  24. HallusionBench

    Datasets & benchmarks

    [CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models

    Stale GitHub, tianyi-lab 344 ★BSD-3-ClauseUpdated 13 months ago

    git clone https://github.com/tianyi-lab/HallusionBench.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.