Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
VideoRAG
AI repositories[KDD'2026] "VideoRAG: Chat with Your Videos"
git clone https://github.com/HKUDS/VideoRAG.git -
Lance
Modelsany to any model by bytedance-research · Lance
bytedance-research/Lance -
ZDTaichu5.0-9B
Modelsimage text to text model by TaichuAI
TaichuAI/ZDTaichu5.0-9B -
Mage-VL
Modelsimage text to text model by microsoft · transformers
microsoft/Mage-VL -
MiMo-V2.5
Modelstext generation model by XiaomiMiMo · transformers
XiaomiMiMo/MiMo-V2.5 -
MiMo-V2.6-Pro-RL
Modelstext generation model by XiaomiMiMo · transformers
XiaomiMiMo/MiMo-V2.6-Pro-RL -
aurora
Datasets & benchmarks[ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
git clone https://github.com/wenhaochai/aurora.git -
MiMo-V2.6-Flash-RL
Modelstext generation model by XiaomiMiMo · transformers
XiaomiMiMo/MiMo-V2.6-Flash-RL -
Video Understanding MCP
MCP serversLet AI agents watch videos and answer questions about them through any OpenAI-compatible endpoint.
@granitebps/video-understanding-mcp@1.0.2 -
video-search-and-summarization
AI repositoriesNVIDIA 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.
git clone https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization.git -
OpenVid-1M
Datasets & benchmarksHugging Face dataset by nkp37
nkp37/OpenVid-1M -
dsh-video-storyboard
Agents & frameworksScene-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.
git clone https://github.com/SAOS-3624/dsh-video-storyboard.git -
telemem
AI repositoriesTeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
git clone https://github.com/TeleAI-UAGI/telemem.git -
Alpie_seed
Modelsimage text to text model by 169Pi · transformers
169Pi/Alpie_seed -
imagine-mcp
MCP serversMCP server for image/video understanding & generation (Gemini/OpenAI/Grok)
imagine-mcp@1.11.6 -
Qwen: Qwen3.8 Omni Flash
ModelsQwen3.8 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,...
qwen/qwen3.8-omni-flash -
StepFun: Step 3.7 Flash
ModelsStep 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...
stepfun/step-3.7-flash -
Xiaomi: MiMo-V2.5
ModelsMiMo-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...
xiaomi/mimo-v2.5 -
Z.ai: GLM 4.5V
ModelsGLM-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,...
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.