# OpenGVLab/Ask-Anything

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

Repository: https://github.com/OpenGVLab/Ask-Anything
Canonical: https://ross.abutalabs.com/products/ask-anything
Homepage: https://vchat.opengvlab.com/
Language: Python
License: MIT
License Family: permissive
Topics: captioning-videos, chatgpt, gradio, langchain, video-question-answering, video-understanding, stablelm, chat, video, big-model, foundation-models, large-language-models, large-model
Last push: 2026-07-17T10:31:09+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 35, longevity 88
- inputs: {"age_days": 1232, "days_push": 47, "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 3346, forks 268 (observed 2026-08-28T04:07:57.627392+00:00)

## What it is
VideoChat/Ask-Anything is a family of multimodal chat models and demos that combine video understanding with large language models, letting users chat about video and image content. It includes VideoChatGPT and successors like VideoChat-Flash and VideoChat3, with Gradio demos and Hugging Face Spaces.

## Use cases
- chat with a bot about a video's content
- generate captions for videos automatically
- answer questions about a video
- build a video question answering app
- run a multimodal video LLM demo
- understand long videos with a multimodal model

## When to choose
- you need video understanding combined with conversational LLMs
- you want pretrained video-chat model weights and demos
- you're researching video question answering or captioning

## When to avoid
- you need production video analytics pipelines rather than chat models
- you lack GPU resources for large multimodal models
- you only need text-only chatbots

## Facets
- artifact type: application
- maturity: active
- function: chatbot, video-processing, llm-inference, machine-learning, nlp
- domain: artificial-intelligence, large-language-models, computer-vision, chatbots
- platform: python
- tags: video-chat, multimodal, video-question-answering, video-captioning, gradio, videochatgpt, foundation-models, video, web-server, gpu

## Member repositories
- OpenGVLab/Ask-Anything (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:57.627392+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 2026-08-29T18:41:00.619644+00:00, confidence not recorded.
  - readme: https://github.com/OpenGVLab/Ask-Anything (fetched 2026-08-28T04:07:57.627392+00:00, sha 2af82e858aa4)
- Data as of 2026-08-30T08:39:29.467469+00:00.