Graphai

<picture> <source media="(prefers-color-scheme: light)" srcset="./docs/images/readme_logo_light.png"> <source media="(prefers-color-scheme: dark)" srcset="./docs/images/readme_logo_dark.png"> <img alt="GraphAI" src="./docs/images/readme_logo_light.png" width="800"> </picture>

GraphAI is an asynchronous data flow execution engine, which allows developers to build agentic applications by describing agent workflows as declarative data flow graphs in YAML or JSON.

Documentation

Official Website

SPECS

• Scientific Paper
• GraphAI core

TypeScript API Document

• API Document
• API Document by typedoc

Agent Document

• Agent Document

Tools

• GraphAI CLI

Application Samples

• Tutorial
• GraphAI samples for developers
• GraphAI samples for end users

Use Case

• Mulmocast
  A CLI tool for generating podcast and video content from script files (MulmoScript). Automates the process of creating audio, images, and video from structured MulmoScript files.
  • GraphAI Agent in Mulmocast
  • GraphData in Mulmocast
    • ./tools/
      • story_to_script.ts
      • create_mulmo_script_interactively.ts
      • create_mulmo_script_from_url.ts
    • ./actions/
      • audio.ts
      • captions.ts
      • images.ts
      • translate.ts

Development

• Collaboration

npm links

GraphAI

https://www.npmjs.com/package/graphai

GraphAI Agents

https://www.npmjs.com/org/graphai

GraphAI Utilities

https://www.npmjs.com/org/receptron

Web demo & tool

GraphAI web demo

https://github.com/receptron/graphai-demo-web

Grapys - GraphAI GUI tool

https://github.com/receptron/grapys