# Forget-C/Jellyfish

An end-to-end production workspace for AI-generated short dramas. From script input to structured storyboarding, consistency management, shot preparation, video generation, and export.

Repository: https://github.com/Forget-C/Jellyfish
Canonical: https://ross.abutalabs.com/products/jellyfish
Homepage: https://forget-c.github.io/Jellyfish
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, short-drama
Last push: 2026-07-30T02:19:18+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 80, longevity 12
- inputs: {"age_days": 180, "days_push": 35, "days_rel": 138, "gap_med": 3.0, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6195, forks 1071 (observed 2026-08-28T04:09:39.601887+00:00)

## What it is
Jellyfish is a self-hosted, end-to-end production workspace for AI-generated short dramas, covering script input, storyboard breakdown, character/scene/prop consistency management, image and video generation, task tracking, and timeline export. It pairs a React + Vite frontend with a FastAPI + LangChain/LangGraph backend, deployable via Docker Compose with MySQL and object storage.

## Use cases
- generate short dramas from scripts with ai
- break a screenplay into shots and storyboards automatically
- keep ai-generated characters and scenes consistent across shots
- manage ai image and video generation tasks in one workspace
- produce episodic video content with ai agents
- self-host an ai video production studio

## When to choose
- you need a full pipeline from script to finished video, not just a single model demo
- character, scene, and prop consistency across many shots is critical
- you want a self-hosted, extensible studio with OpenAPI-based integration and multi-model support

## When to avoid
- you only need a quick one-off text-to-video generation without production workflow
- you want a fully managed cloud SaaS rather than self-hosting Docker services
- your project is unrelated to scripted drama or episodic video content

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, image-processing, video-processing, workflow-automation, web-framework, gui, prompt-engineering
- domain: artificial-intelligence, media, web-development
- platform: self-hosted, python, cross-platform
- tags: ai-video-generation, storyboarding, short-drama, script-breakdown, character-consistency, fastapi, react, langchain, video-production, self-hosted-studio, ai-agents, video, automation, docker, web-server

## Member repositories
- Forget-C/Jellyfish (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:39.601887+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 2026-08-29T17:47:21.331269+00:00, confidence not recorded.
  - readme: https://github.com/Forget-C/Jellyfish (fetched 2026-08-28T04:09:39.601887+00:00, sha d4b2d00b6b2d)
  - homepage: https://forget-c.github.io/Jellyfish (fetched 2026-08-29T08:43:49.441028+00:00, sha 099e509db1e9)
- Data as of 2026-08-30T08:39:29.467469+00:00.