InnerVault

Library

85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

3,844 results with any of your words Clear search and filters
  1. multimodal

    MCP servers

    Multi-provider media generation — images, video, audio, and transcription via a unified interface

    Stale Official MCP Registry, io.github.rsmdt Updated 8 months ago 2 notes

    @r16t/multimodal-mcp@1.3.1
  2. visual document retrieval model by nvidia · vllm

    Stale Hugging Face Hub, nvidia 22 ♥otherUpdated 27 days ago

    nvidia/Nemotron-3.5-Embed-1B-NVFP4
  3. Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...

    Indexed OpenRouter model list, qwen Updated 13 months ago

    qwen/qwen3-vl-30b-a3b-instruct
  4. [GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...

    Indexed OpenRouter model list, openai Updated 7 months ago

    openai/gpt-5.4-image-2
  5. image text to text model by DavidAU

    Indexed Hugging Face Hub, DavidAU 92 ♥apache-2.0Updated 6 days ago

    DavidAU/Qwen3.8-40B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF
  6. image text to text model by DavidAU

    Indexed Hugging Face Hub, DavidAU 312 ♥apache-2.0Updated 7 days ago

    DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF
  7. visual document retrieval model by nvidia · sentence-transformers

    Stale Hugging Face Hub, nvidia 31 ♥otherUpdated 27 days ago

    nvidia/Nemotron-3.5-Embed-8B-BF16
  8. image text to text model by DavidAU

    Indexed Hugging Face Hub, DavidAU 199 ♥apache-2.0Updated 8 days ago

    DavidAU/Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF
  9. pdf4vllm

    MCP servers

    PDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.

    Stale Official MCP Registry, io.github.PyJudge Updated 11 months ago 1 note

    pdf4vllm-mcp@1.0.2
  10. Vision-Agents

    Agents & frameworks

    Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

    Stale GitHub, GetStream 8,201 ★Apache-2.0Updated 14 days ago

    git clone https://github.com/GetStream/Vision-Agents.git
  11. Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...

    Indexed OpenRouter model list, elorian Updated 31 days ago

    elorian/glimpse
  12. Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...

    Indexed OpenRouter model list, mistralai Updated 42 days ago

    mistralai/mistral-large-4-0
  13. inference

    AI repositories

    Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.

    Indexed GitHub, xorbitsai 9,660 ★Apache-2.0Updated yesterday

    git clone https://github.com/xorbitsai/inference.git
  14. Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...

    Indexed OpenRouter model list, amazon Updated 23 months ago

    amazon/nova-lite-v1
  15. Multimodal image privacy filter stripping GPS coordinates, device serials, and sensitive EXIF markers

    Stale GitHub, alphaparkinc 7 ★Updated 23 days ago

    git clone https://github.com/alphaparkinc/genpark-multimodal-exif-geotag-privacy-sanitizer-skill.git
  16. pardesline

    MCP servers

    3D vision and medical imaging: 43 datasets with licences, 73 algorithms on clouds, meshes, CT/MRI

    Indexed Official MCP Registry, io.github.pardesline Updated yesterday 2 notes

    pardesline@0.5.0
  17. mlx-vlm

    AI repositories

    MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

    Indexed GitHub, Neywa-Labs 5,848 ★MITUpdated 2 days ago

    git clone https://github.com/Neywa-Labs/mlx-vlm.git
  18. MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

    Indexed OpenRouter model list, minimax Updated 5 months ago

    minimax/minimax-m3
  19. Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...

    Indexed OpenRouter model list, qwen Updated 6 months ago

    qwen/qwen3.6-27b
  20. Multimodal image privacy filter stripping GPS coordinates, device serials, and sensitive EXIF markers

    Stale GitHub, Alpha-Park 7 ★Updated 23 days ago

    git clone https://github.com/Alpha-Park/genpark-multimodal-exif-geotag-privacy-sanitizer-skill.git
  21. Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

    Indexed OpenRouter model list, google Updated 7 months ago

    google/gemma-4-31b-it
  22. MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

    Indexed OpenRouter model list, minimax Updated 5 months ago

    minimax/minimax-m3:batch
  23. dsh-video-storyboard

    Agents & frameworks

    Scene-aware storyboard for DeepSeek Harness: 9-16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.

    Indexed GitHub, SAOS-3624 552 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/SAOS-3624/dsh-video-storyboard.git
  24. Pareto 26.9

    Models

    Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

    Indexed OpenRouter model list, unbiased Updated 35 days ago

    unbiased/pareto-26.9

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.