Video Understanding Python Packages

lmms-eval

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

nybls

Low cost, iterative video watching for AI agents. Transcript first, then only the frames it asks for, with receipts.

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

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.

paddlevideo

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.

telemem

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

vidchain

✅A Lightweight Video RAG Framework for Multimodal Reasoning

vidxp

VidXP (Video eXPlain) - Video Indexing Engine. Search in videos in natural language. 👀 Connect your Hermes / Claude / OpenClaw agents, allow them to understand videos with low token cost.

vid2llm

Turn any video into LLM-ready frames. Smart sampling, scene detection, OCR, and SDK-ready output for modern multimodal language models.

framesieve

Search long video without running a VLM on every frame. Index once with a small encoder, spend the expensive model only where it matters.

video2tfrecord

Easily convert RGB video data (e.g. .avi) to the TensorFlow tfrecords file format for training e.g. a NN in TensorFlow. This implementation allows to limit the number of frames per video to be stored in the tfrecords.

ppvideo

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.

habench

Video Generation Benchmark

vss-ctx-rag

Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.

videobench

Video Generation Benchmark

videomind

Self-hostable video-understanding stack: FastAPI + Vue workbench + CLI/Agent Skill. Turn videos into structured notes, articles, cards, or teaching pages.

mmaction

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

live-bench

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

otxmmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark