InnerVault

Library

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

Results

11,719 results with any of your words Clear search and filters
  1. replicate-mcp-server

    MCP servers

    Replicate MCP server - image, video, audio, speech, LLM, vision, upscale, 3D, training. 36 tools.

    Stale Official MCP Registry, io.github.sena-labs Updated 21 days ago 1 note

    replicate-mcp-server@3.3.1
  2. any to any model by LiquidAI · gguf

    Indexed Hugging Face Hub, LiquidAI 182 ♥otherUpdated 14 days ago

    LiquidAI/LFM3-Omni-2B-GGUF
  3. image text to text model by unsloth

    Stale Hugging Face Hub, unsloth 48 ♥otherUpdated 22 days ago

    unsloth/MiniMax-M3.1-Flash-GGUF
  4. The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

    Indexed OpenRouter model list, openai Updated 2 years ago

    openai/gpt-4-turbo:batch
  5. suno

    Datasets & benchmarks

    Hugging Face dataset by nyuuzyou

    Stale Hugging Face Hub, nyuuzyou 158 ♥cc0-1.0Updated 9 months ago

    nyuuzyou/suno
  6. aurora

    Datasets & benchmarks

    [ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

    Stale GitHub, wenhaochai 149 ★Apache-2.0Updated 17 months ago

    git clone https://github.com/wenhaochai/aurora.git
  7. Callirra

    MCP servers

    Create images, video and audio; chat with multimodal AI; manage assets and reusable workflows.

    Stale Official MCP Registry, io.github.callirra-ai Updated 24 days ago 1 note

    @callirra/mcp@0.3.1
  8. Mixpeek

    MCP servers

    Give your agent eyes. Search video, images, and audio via the Mixpeek multimodal retrieval API.

    Stale Official MCP Registry, io.github.mixpeek Updated 7 months ago 2 notes

    @mixpeek/mcp@0.1.1
  9. NVIDIA 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.

    Indexed GitHub, NVIDIA-AI-Blueprints 1,986 ★Apache-2.0Updated yesterday

    git clone https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization.git
  10. feature extraction model by facebook · transformers

    Indexed Hugging Face Hub, facebook 40 ♥Updated today

    facebook/meta-encoder-v1
  11. awesome-agent-apis

    AI repositories

    660+ muapi-hosted generative-media models plus community-submitted third-party API tools (SEO, enrichment, social, scraping) — one YAML file per entry, browsable by capability.

    Stale GitHub, Anil-matcha 1,057 ★MITUpdated 34 days ago

    git clone https://github.com/Anil-matcha/awesome-agent-apis.git
  12. d3

    Models

    zero shot classification model by vllm-sr · transformers

    Stale Hugging Face Hub, vllm-sr 273 ♥apache-2.0Updated 26 days ago

    vllm-sr/d3
  13. A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

    Indexed OpenRouter model list, mistralai Updated 11 months ago

    mistralai/ministral-8b-2512
  14. The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

    Indexed OpenRouter model list, mistralai Updated 11 months ago

    mistralai/ministral-3b-2512
  15. Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

    Indexed OpenRouter model list, google Updated 20 months ago

    google/gemma-3-4b-it
  16. Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

    Indexed OpenRouter model list, google Updated 20 months ago

    google/gemma-3-12b-it
  17. Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

    Indexed OpenRouter model list, google Updated 20 months ago

    google/gemma-3-27b-it
  18. WeVisCut

    Models

    any to any model by tencent · transformers

    Stale Hugging Face Hub, tencent 26 ♥otherUpdated 18 days ago

    tencent/WeVisCut
  19. 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
  20. d3-flash

    Models

    zero shot classification model by vllm-sr · transformers

    Stale Hugging Face Hub, vllm-sr 84 ♥apache-2.0Updated 31 days ago

    vllm-sr/d3-flash
  21. d3-turbo

    Models

    zero shot classification model by vllm-sr · transformers

    Stale Hugging Face Hub, vllm-sr 130 ♥apache-2.0Updated 15 days ago

    vllm-sr/d3-turbo
  22. LivePortrait

    Tools & apps

    Hugging Face space by KlingTeam

    Indexed Hugging Face Hub, KlingTeam 3,825 ♥Updated 2 years ago 1 note

    KlingTeam/LivePortrait
  23. Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

    Indexed OpenRouter model list, thinkingmachines Updated 3 months ago

    thinkingmachines/inkling-small
  24. VideoGLaMM

    Agents & frameworks

    [CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

    Stale GitHub, mbzuai-oryx 106 ★Updated 2 months ago

    git clone https://github.com/mbzuai-oryx/VideoGLaMM.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.