Toonflow is an AI-driven short drama production tool that automates the conversion of novels into scripts and generates images and videos, streamlining the entire short drama creation process.
Source: per README View on GitHub →Toonflow is gaining attention due to its ability to automate the complex process of short drama production, addressing the pain points of manual scriptwriting and video production. Its unique technical choices, such as the three-tiered Agent collaboration system and persistent Agent memory, stand out for their efficiency and scalability.
Source: Synthesis of README and project traitsOrganizes scripts, characters, storyboards, assets, and video nodes in an infinite canvas format, allowing for free arrangement, rollback, and parallel production without linear step constraints.
Source: per READMEInvolves decision-making, execution, and supervision layers working together to cover task decomposition, content generation, quality review, and revision feedback, enhancing stability and consistency of the final product.
Source: per READMEBased on local ONNX vector retrieval, this system supports short-term messages, long-term summaries, and semantic recall, ensuring continuity in multi-round creation.
Source: per READMESupports writing TypeScript logic directly in the settings center and applying it instantly without modifying source code or restarting, facilitating privatization and multi-model integration.
Source: per READMEAutomatically extracts chapter events from the original work and structures them for storage, allowing script adaptation to precisely call context based on event graphs, reducing loss of long text information.
Source: per READMEThe core prompts of ScriptAgent and ProductionAgent are externalized into Markdown Skill files, supporting online editing and rapid optimization.
Source: per READMEThe architecture inferred from the code structure and dependencies suggests a modular design with clear separation of concerns. Key technical decisions include the use of Electron for the GUI, Node.js for server-side logic, and Docker for containerization. The data flow is likely to involve a client-server model with heavy reliance on AI services for content generation.
Source: Code tree + dependency filesCenter: project; inner ring: core feature modules; outer ring: key dependencies. Auto-generated from core_features and tech_stack.key_deps.
@ai-sdk/anthropic@ai-sdk/deepseek@ai-sdk/devtools@ai-sdk/google@ai-sdk/openai@ai-sdk/openai-compatible@ai-sdk/xai@huggingface/transformers@rmp135/sql-tsaxiosaxios-retrybetter-sqlite3compressingcorsdotenvexpressexpress-wsfast-globform-datagraphlibToonflow is suitable for short video content creation, novel adaptation experiments, AI literary adaptation tools, script development and rapid prototyping, and video material generation.
Source: READMEv1.1.7 (2026-05-01): ToonFlow v1.1.7
Source: GitHub ReleasesToonflow is a promising project for teams and individuals looking to automate and streamline the process of short drama production. Its integration of AI technology and comprehensive feature set makes it a valuable tool for content creators and developers in the entertainment industry.