video-understanding repositories
Trending repositories tagged video-understanding, ranked by trending score. Updated daily.
-
1
SAOS-3624/dsh-video-storyboard
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.
GitHub · JavaScript · 584 stars · 41 forks · +9 stars in 24 hours · Trending score 2.13
-
2
bytedance/Lance
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
GitHub · Python · 1,370 stars · 92 forks · +22 stars in 24 hours · Trending score 2.04
-
3
oxbshw/watch-skill
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.
GitHub · Python · 586 stars · 84 forks · 0 stars in 24 hours · Trending score 1.69
-
4
Tencent/WeMM-Video
WeMM-Video is a family of omni-modal foundation models by WeChat Vision at Tencent, excelling in omni-modal video understanding and reasoning while maintaining top-tier capabilities across general audio, image, and text.
GitHub · Python · 58 stars · 2 forks · +21 stars in 24 hours · Trending score 1.53
-
5
Aseiel/VideoHighlighter
Open-source local AI video analyzer powered by Ollama. Visual search, automatic highlights, scene/action/object detection, audio analysis, and subtitle generation. Free, offline alternative to Twelve Labs, Runway, and Descript.
GitHub · Python · 481 stars · 61 forks · 0 stars in 24 hours · Trending score 1.28
-
6
OmniJev/OneJev
🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forward pass.
GitHub · Python · 274 stars · 28 forks · 0 stars in 24 hours · Trending score 1.26
-
7
UditAkhourii/cdaf
CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skill, reproducible benchmark.
GitHub · Python · 226 stars · 12 forks · 0 stars in 24 hours · Trending score 1.21
-
8
devinxzhang/CycleGRPO
[ECCV 2026] Official code for CycleGRPO and its video extension Generalized CycleGRPO — unifying region understanding and localization via caption-grounding cycle-consistency RL
GitHub · Python · 18 stars · 0 forks · +2 stars in 24 hours · Trending score 0.98
-
9
rhfeiyang/GEB
Official implementation of "Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies"
GitHub · 62 stars · 0 forks · +3 stars in 24 hours · Trending score 0.91
-
10
NVIDIA-AI-Blueprints/video-search-and-summarization
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.
GitHub · Python · 1,997 stars · 421 forks · 0 stars in 24 hours · Trending score 0.85
-
11
EvolvingLMMs-Lab/lmms-eval
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
GitHub · Python · 4,497 stars · 699 forks · 0 stars in 24 hours · Trending score 0.80
-
12
NVIDIA/context-aware-rag
Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.
GitHub · Python · 94 stars · 31 forks · 0 stars in 24 hours · Trending score 0.52
-
13
MuseLinn/MusePi
MusePi — desktop-first AI coding assistant: Electron GUI + TUI/CLI + daemon + desktop companion. Native video understanding, MCP, advisor, memory, multi-domain skills; own update channel.
GitHub · TypeScript · 21 stars · 1 forks · 0 stars in 24 hours · Trending score 0.38
-
14
The-Martyr/Awesome-Multimodal-Reasoning
Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal LLMs
GitHub · 108 stars · 13 forks · 0 stars in 24 hours · Trending score 0.28
-
15
MirroS-Lab/Code-as-World
Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning
GitHub · Python · 452 stars · 10 forks · 0 stars in 24 hours · Trending score 0.22
-
16
Lechoung-J/reelpack-alpha
Reelpack — 给 AI 的视频理解引擎 / The Video-Understanding Engine for AI · License: FSL-1.1-MIT
GitHub · Python · 199 stars · 0 forks · 0 stars in 24 hours · Trending score 0.19
-
17
junnhwan/vid-lens
基于 Go 与 Eino 的多模态视频解读 Agent:阅读转写文本/字幕、按需查看真实画面,将 YouTube 视频整理为图文文章,支持围绕原视频持续问答。
GitHub · Go · 76 stars · 10 forks · 0 stars in 24 hours · Trending score 0.18
-
18
ambient-intelligence-hq/ambient
A video understanding and research agent that can reason over long-form videos
GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.10
-
19
momentslab/peek
[BMVC 2026] Official implementation of PEEK: Picking Essential frames via Efficient Knowledge distillation
GitHub · Python · 21 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
20
OpenMOSS/MOSS-VL
An open-weight 11B model series for long-form and real-time video understanding
GitHub · C++ · 838 stars · 46 forks · 0 stars in 24 hours · Trending score 0.00
-
21
TeleAI-UAGI/telemem
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
GitHub · Python · 495 stars · 36 forks · 0 stars in 24 hours · Trending score 0.00
-
22
iBz-04/boomerang
Exact-moment video search & retrieval
GitHub · Rust · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
23
bytedance/SALMONN
SALMONN family: A suite of advanced multi-modal LLMs
GitHub · 1,576 stars · 130 forks · 0 stars in 24 hours · Trending score 0.00
-
24
zai-org/GLM-V
GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
GitHub · Python · 2,406 stars · 194 forks · 0 stars in 24 hours · Trending score 0.00