# HKUDS/VideoAgent

"VideoAgent: All-in-One Agentic Framework for Video Understanding, Editing, and Remaking"

Repository: https://github.com/HKUDS/VideoAgent
Canonical: https://ross.abutalabs.com/products/videoagent
Homepage: https://arxiv.org/abs/2606.23327
Language: Python
License: MIT
License Family: permissive
Topics: agents, llm-agents, video-editing, video-understanding, notebooklm, audio-editing, audio-understanding, podcast
Last push: 2026-07-22T01:44:05+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 93, release rhythm 35, longevity 29
- inputs: {"age_days": 413, "days_push": 43, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1753, forks 233 (observed 2026-08-28T04:05:31.813575+00:00)

## What it is
VideoAgent is an all-in-one agentic framework for video understanding, editing, and remaking, built on multi-agent orchestration with over thirty specialized editing agents. It enables natural-language-driven video Q&A, summarization, clip editing, and generative video creation with cross-modal retrieval and shot planning.

## Use cases
- summarize long videos automatically
- ask questions about video content
- edit video clips via natural language commands
- remake or generate new video content with AI
- create video overviews like NotebookLM-style podcasts
- analyze audio and video together for insights

## When to choose
- you want conversational, LLM-driven video editing and understanding
- you need multi-modal analysis combining audio and video
- you want an extensible multi-agent pipeline for video production

## When to avoid
- you need lightweight, deterministic video processing without LLM API costs
- you require frame-accurate professional NLE editing
- you need offline operation without cloud model access

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, video-processing, audio-processing, machine-learning, nlp
- domain: artificial-intelligence, media
- platform: python, cross-platform
- tags: video-understanding, video-editing, llm-agents, multi-modal, podcast, notebooklm, video, ai-agents, natural-language-processing

## Member repositories
- HKUDS/VideoAgent (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:31.813575+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:28:09.589399+00:00, confidence not recorded.
  - readme: https://github.com/HKUDS/VideoAgent (fetched 2026-08-28T04:05:31.813575+00:00, sha a3d72dd654b6)
  - homepage: https://arxiv.org/abs/2606.23327 (fetched 2026-08-29T11:06:17.212776+00:00, sha e3a4e9ba2f0b)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:06:17.219720+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:06:17.215758+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:06:17.222130+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:06:17.217773+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.