InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. VideoRAG

    AI repositories

    [KDD'2026] "VideoRAG: Chat with Your Videos"

    Stale GitHub, HKUDS 3,398 ★Custom licence (see repository)Updated 8 months ago

    git clone https://github.com/HKUDS/VideoRAG.git
  2. Lance

    Models

    any to any model by bytedance-research · Lance

    Stale Hugging Face Hub, bytedance-research 1,065 ♥apache-2.0Updated 5 months ago

    bytedance-research/Lance
  3. image text to text model by TaichuAI

    Indexed Hugging Face Hub, TaichuAI 3,044 ♥Updated 57 days ago

    TaichuAI/ZDTaichu5.0-9B
  4. Mage-VL

    Models

    image text to text model by microsoft · transformers

    Stale Hugging Face Hub, microsoft 430 ♥apache-2.0Updated 3 months ago

    microsoft/Mage-VL
  5. MiMo-V2.5

    Models

    text generation model by XiaomiMiMo · transformers

    Stale Hugging Face Hub, XiaomiMiMo 431 ♥mitUpdated 4 months ago

    XiaomiMiMo/MiMo-V2.5
  6. text generation model by XiaomiMiMo · transformers

    Stale Hugging Face Hub, XiaomiMiMo 816 ♥mitUpdated 19 days ago

    XiaomiMiMo/MiMo-V2.6-Pro-RL
  7. 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
  8. text generation model by XiaomiMiMo · transformers

    Stale Hugging Face Hub, XiaomiMiMo 582 ♥mitUpdated 38 days ago

    XiaomiMiMo/MiMo-V2.6-Flash-RL
  9. Let AI agents watch videos and answer questions about them through any OpenAI-compatible endpoint.

    Stale Official MCP Registry, io.github.granitebps Updated 3 days ago 2 notes

    @granitebps/video-understanding-mcp@1.0.2
  10. 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 today

    git clone https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization.git
  11. OpenVid-1M

    Datasets & benchmarks

    Hugging Face dataset by nkp37

    Indexed Hugging Face Hub, nkp37 300 ♥cc-by-4.0Updated 7 months ago

    nkp37/OpenVid-1M
  12. 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 yesterday

    git clone https://github.com/SAOS-3624/dsh-video-storyboard.git
  13. telemem

    AI repositories

    TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.

    Stale GitHub, TeleAI-UAGI 493 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/TeleAI-UAGI/telemem.git
  14. Alpie_seed

    Models

    image text to text model by 169Pi · transformers

    Stale Hugging Face Hub, 169Pi 27 ♥apache-2.0Updated 4 days ago

    169Pi/Alpie_seed
  15. imagine-mcp

    MCP servers

    MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)

    Stale Official MCP Registry, io.github.n24q02m Updated 2 months ago 2 notes

    imagine-mcp@1.11.6
  16. Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...

    Indexed OpenRouter model list, qwen Updated 56 days ago

    qwen/qwen3.8-omni-flash
  17. Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

    Indexed OpenRouter model list, stepfun Updated 5 months ago

    stepfun/step-3.7-flash
  18. MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

    Indexed OpenRouter model list, xiaomi Updated 6 months ago

    xiaomi/mimo-v2.5
  19. GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

    Indexed OpenRouter model list, z-ai Updated 15 months ago

    z-ai/glm-4.5v

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.