Skip to content
forked from ai-shifu/ai-shifu

LLM-powered AI that leads and drives intelligent conversations

License

Notifications You must be signed in to change notification settings

sunner/ai-shifu

 
 

Repository files navigation

Shifu (master) mode: Human-led, AI-delivered, user follows, interaction at any time

English | 简体中文

AI-Shifu is a guide powered by LLM. Unlike other human-led chatbots, AI-Shifu is AI-led chat flow, and humans just need to follow. Although in the process, humans can ask questions at any time and affect the content of the conversation, it will eventually return to the AI-led storyline. And AI can make personalized output based on user identity, interests, and preferences, making users feel like they are being served one-on-one. In education, storytelling, product guides, surveys, and game NPC scenarios, AI-Shifu can provide a more interactive and immersive experience.

GitHub stars GitHub followers

Features

  1. Controllable Chat Flow: Use preset prompts to constrain AI's output and control the chat process.
  2. Interactive: Allow asking questions to the user and obtaining feedback.
  3. Personalized: Make personalized output based on user input such as identity, interests, and preferences.
  4. Q & A: Ask questions based on context at any time to get more information.
  5. Script Development Environment: Use Lark multi-dimensional tables as an editor, combined with a debugger, to easily debug script prompts.

Roadmap

  • Better script development environment, abandon the dependency on Lark
  • Refactor the user experience of Q & A
  • Support knowledge base
  • Continuous output mode
  • Speech input and output

Using AI-Shifu

Platform

AI-Shifu.com is an education platform powered by AI-Shifu. You can try it and learn the AI-guided courses developed by human experts.

Self-hosting

Quickly get AI-Shifu running in your environment with this starter guide.

Quick Start

Coming soon...

About

LLM-powered AI that leads and drives intelligent conversations

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 69.2%
  • JavaScript 23.7%
  • SCSS 3.9%
  • Shell 2.0%
  • CSS 0.5%
  • Dockerfile 0.4%
  • Other 0.3%