MovieAgent: automated movie generation via multi-agent CoT planning
Source: https://github.com/showlab/movieagent
Structured fields
{
"archived": false,
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "Multi-agent planner that turns a script synopsis and a character bank into scenes, shots and camera settings (director, screenwriter, storyboard artist and location manager roles) feeding video generation.",
"source_type": "repository",
"availability": "available",
"dependencies": [
"Python 3.8",
"conda"
],
"source_owner": "Show Lab (NUS) and collaborators",
"next_check_at": "2026-10-31T00:00:00.000Z",
"known_limitations": [
"No license; unverified end-to-end behaviour."
],
"upstream_updated_at": "2025-03-26T13:00:54.000Z"
}Evidence claims
- [upstream_claim] README abstract: given a script and character bank, MovieAgent generates multi-scene, multi-shot long videos with hierarchical CoT planning and role-playing LLM agents. · locator: README abstract source
- [sourced_fact] README install instructions: conda env with Python 3.8 and requirements.txt; dataset layout uses script_synopsis.json and per-character photos/audio. · locator: Installation and Model and Data Preparation sections source
- [sourced_fact] No license file detected by GitHub; last push 2025-03-26. · locator: repository metadata source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | unknown | unknown | unknown | unknown | unknown | No license file; treat code rights as unknown. Paper is CC BY 4.0 on arXiv (https://arxiv.org/abs/2503.07314). |
| model_weights | unknown | unknown | unknown | unknown | unknown | Depends on external generation models whose terms were not checked. |