@difizen/ai-flow
Version:
Scalable, out-of-the-box, agent-oriented flow
21 lines (16 loc) • 1.16 kB
Markdown
## Out-of-the-box Agent Workflow solutions

<p align="center">
<a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
<a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
</p>
The core of the canvas is the paradigm of the canvas, which is manifested in nodes, connectivity, and data flow management
This solution expects to cover both paradigms: process orchestration and configuration assembly. And comprehensive canvas capabilities are built-in.
- AI featured custom nodes, including input and output of its own configuration items, support for running results view
- Canvas supports data flow, variable referencing and streaming
- Unified Schema, users only need to care about the data layer access, define the data structure in line with the Schema
- Support code customization nodes
- Built-in canvas basic capabilities , undo redo , auto-save , layout optimization and so on.
- Nested workflow logic
- Built-in AI featured front-end components
- Support for light and dark color themes