Crayotter
🦦 Crayotter: A Multimodal AI-Agent for Video-Editing, Video-Composing, and Video Production. Powered by Multimodal LLMs for autonomous Text-to-Video agentic framework. | 基于多模态大模型 (Multimodal LLMs) 的 AI 剪辑智能体，支持从文字需求到视频成品的端到端全自动生产与创作。
Last verified:
What is Crayotter?
Crayotter is a multimodal AI-Agent for video-editing, video-composing, and video production. It is an agent-driven video automatic editing system that can convert a single text requirement into a complete finished video. The tool is powered by Multimodal LLMs for autonomous Text-to-Video agentic framework.
The workflow consists of three automated phases: planning (规划), deep editing research (深度剪辑研究), and automatic generation (自动生成). First it plans the video structure, then analyzes and searches for relevant footage, and finally automatically edits and exports the complete video. This splits video generation into a three-stage automated workflow.
Key features include multimodal input support, agent-driven automation, one-sentence video search and clipping, local deployment capability, integrated search and analysis, automatic clipping and export全流程 (full process), and general agent framework architecture. It supports material preparation, deep research, and automatic generation.
Crayotter is designed for content creators, video editors, social media managers, marketers, and anyone who needs to create edited videos from text descriptions without manual editing skills. It's suitable for those who want to automate video production workflows.
Crayotter pricing
Pricing model: Freemium
Free and open source. The project is available on GitHub under the idwts/Crayotter repository. No paid plans mentioned. Users need to provide their own multimodal LLM API access for the AI capabilities. Local deployment is supported.
Crayotter pros
- Turns single text request into complete edited video
- Multimodal AI-Agent architecture
- Three-phase automated workflow
- Planning phase for video structure
- Deep editing research for quality
- Automatic generation and export
- One-sentence video search capability
- Local deployment supported
- Powered by multimodal LLMs
- Autonomous text-to-video processing
- Integrated search and clipping
- Full process automation from search to export
- General agent framework design
- Material preparation automation
- No manual editing skills required
Crayotter cons
- Requires multimodal LLM API access
- New project with limited documentation
- May need technical setup for local deployment
- Limited to text-to-video workflow
- Depends on AI model quality
- May not support all video formats
- Research phase may take time
- Open source with no commercial support
Frequently asked questions about Crayotter
What is Crayotter?
Crayotter is a multimodal, agent-driven video editing system that turns a single text request into a complete edited video. It is powered by Multimodal LLMs for autonomous Text-to-Video agentic framework.
How does the Crayotter workflow work?
The workflow consists of three automated phases: planning (规划), deep editing research (深度剪辑研究), and automatic generation (自动生成). First it plans the video, then analyzes and searches for footage, and finally automatically edits and exports.
What can I use Crayotter for?
Crayotter is used for video-editing, video-composing, and video production. It can convert text requirements into complete finished videos automatically.
Do I need to install anything?
Crayotter supports local deployment. You can clone the repository from GitHub at idwts/Crayotter and set it up locally on your machine.
What AI models does Crayotter use?
Crayotter is powered by Multimodal LLMs (Large Language Models) for its autonomous text-to-video agentic framework capabilities.
Is Crayotter free to use?
Yes, Crayotter is open source and available for free on GitHub. However, users may need to provide their own multimodal LLM API access for the AI capabilities.
Can I search for videos with Crayotter?
Yes, Crayotter supports one-sentence video search and clipping. It can automatically search for relevant video footage based on your text description.
What is the project status?
Crayotter is an active open source project on GitHub with issues and pull requests. It was recently introduced in May 2026.
Who is Crayotter for?
Crayotter is for anyone who wants to create edited videos from text descriptions without manual editing. Content creators, video editors, and marketers can benefit from its automation.
How do I get started with Crayotter?
Visit the GitHub repository at https://github.com/idwts/Crayotter to clone the project. The website is at https://idwts.github.io/Crayotter/ for more information.