# HITsz-TMG/VideoClaw

🚀 AI 全自动化视频生成员工 | Your First AIGC Coworker. Chat an Idea. Get a Film. 🦞

Repository: https://github.com/HITsz-TMG/VideoClaw
Canonical: https://ross.abutalabs.com/products/videoclaw
Language: Python
License: MIT
License Family: permissive
Topics: filmmaking, agent, openclaw, openclaw-skills, multi-agent-system, aigc, video-generation, image-generation, tts
Last push: 2026-08-26T05:31:29+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 52
- inputs: {"age_days": 734, "days_push": 7, "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 1724, forks 256 (observed 2026-08-28T04:05:27.994562+00:00)

## What it is
VideoClaw is an AI director system that turns a one-line idea or story synopsis into a fully automated video production pipeline, covering script planning, character/scene design, storyboarding, reference image generation, video generation, and post-production editing. It exposes a WebUI and integrates with OpenClaw so users can chat an idea and receive a finished film while inspecting and editing intermediate assets at every stage.

## Use cases
- generate a complete video from a one-sentence idea
- automate script writing, storyboarding, and shot planning for short films
- create narrated short videos with AI voiceover
- produce digital human talking-head videos
- make serialized short dramas with infinite continuation of the plot
- generate videos from first frame, first-last frames, or reference images
- run an end-to-end AIGC video production workflow locally

## When to choose
- you want fully automated idea-to-film generation with editable intermediate outputs
- you need a multi-stage pipeline (script, storyboard, images, video, editing) rather than a single text-to-video model
- you want OpenClaw integration or a self-hosted WebUI for configuring models and APIs

## When to avoid
- you only need a simple one-shot text-to-video model call without pipeline control
- you require commercial-grade guaranteed video quality or SLAs
- you cannot provide API keys or local compute for the underlying generation models

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, video-processing, image-processing, tts, llm-inference, workflow-automation
- domain: artificial-intelligence, media, large-language-models
- platform: python, cross-platform, self-hosted
- tags: aigc, video-generation, multi-agent, filmmaking, storyboard, text-to-video, openclaw, webui, ai-agents, video

## Member repositories
- HITsz-TMG/VideoClaw (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:27.994562+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 2026-08-30T03:33:53.802186+00:00, confidence not recorded.
  - readme: https://github.com/HITsz-TMG/VideoClaw (fetched 2026-08-28T04:05:27.994562+00:00, sha b7f70799be7f)
- Data as of 2026-08-30T08:39:29.467469+00:00.