Skip to content

matchcase/yui

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Yui

A feature-rich, LangGraph-based Multimodal Agentic Discord bot with long-term memory!

Example usage of the bot

Features

  • 🧠 Long-term conversation memory using ChromaDB
  • 📷 Supports multimodal media like images
  • 🤖 Supports Google, OpenAI, Anthropic and even local models
  • 🌐 (Tool) Can search the web and crawl webpages
  • 🔔 (Tool) Can set reminders for users and ping them
  • ☑️ (Tool) Can maintain TODO lists for users
  • 🎲 (Tool) Can roll dice (you can specify the number of die and faces!)

Setup

Before running the bot, make sure that you have a local SearxNG instance running, as this will be used to do web searches. First, set up a virtual environment and install the dependencies:

python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install -r requirements.txt

Next, run the bot:

python3 main.py

You will be prompted to provide values for your Discord token, provider API token (or Ollama model name) and user ID. Your bot should be up and running now!

Planned features

  • Multimodal model integration
  • Context window and idling-based memory management
  • Slash commands for tools
  • Tool for creating polls
  • Tool for captioning images
  • Tool for searching GIFs

License

This repository is licensed under AGPLv3 or later. © Sarthak Shah (matchcase), 2025

About

A Feature-rich, LangGraph-based Multimodal Agentic Discord bot with Long-Term Memory

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages