[opensourcedex]

GPTDiscord is a free, open source ai interaction & interfaces project written in Python and released under MIT. It has 1,852 GitHub stars, 290 forks and 44 open issues, and was last pushed 7 months ago. On this registry it ranks #98 of 135 tracked projects in AI Interaction & Interfaces, with 5 head-to-head comparisons available.

What is GPTDiscord?

GPTDiscord is a self-hostable, all-in-one OpenAI and GPT integration for Discord that packages ChatGPT-style conversation, DALL-E image generation, AI moderation, custom document indexes and a YouTube summariser into one bot for Discord server owners, moderators and communities that want those features inside their own server.

What it is

GPTDiscord is an open-source Python bot, licensed MIT and maintained by Kav-K, that exposes OpenAI's models as Discord commands. It is distributed two ways: as the PyPI package gpt3discord and as a Docker image produced by the project's build-and-publish-docker.yml workflow. The codebase is asynchronous, built around asyncio, and the README describes it as a robust, all-in-one OpenAI integration for Discord with feature parity with ChatGPT web. The project lives in the Discord bot ecosystem and depends on outside services: the OpenAI API for models and DALL-E, a vector database for embeddings and retrieval, and E2B for code execution and environment manipulation.

The concrete problem it solves is fragmentation. Without it, a server that wants conversational chat, image generation, moderation, document Q&A and code interpretation typically needs several separate bots, or members leave Discord for the ChatGPT web interface. GPTDiscord replaces that scattering of tools with a single bot that answers through slash commands such as /gpt converse, so the workspace, its permissions, its moderation and its knowledge base stay in one place. It also replaces Pinecone as the vector store backing, with the project migrating towards Qdrant.

Key capabilities

  • Multi-modal conversation: images sent to the bot during a /gpt converse thread are understood and answered.
  • DALL-E image generation, alongside drawing mode referenced in the multi-modality update.
  • Code Interpreter and Advanced Data Analysis, running code and manipulating environments through E2B.
  • Custom indexes and document Q&A over your own documents, built on embeddings, with vector storage moving to Qdrant.
  • Internet-connected chat with Wolfram Alpha and Google access, including link crawling.
  • AI moderation of server content.
  • YouTube summariser, translations, language detection, permanent memory, AI-search, user-input API keys and configurable permissions.

Who uses it and how

  • Discord community servers that want AI moderation and conversational chat in one bot rather than several per-feature bots.
  • Teams and researchers who index their own documents for Q&A, using custom indexes and embeddings.
  • Members running advanced data analysis or code interpretation inside Discord through the E2B-backed interpreter.
  • Self-hosters deploying on a DigitalOcean Droplet, following the project's Droplet guide.
  • Servers where members bring their own OpenAI keys through the user-input API key feature, so the owner does not fund every request.

Getting started

Install the bot as the PyPI package gpt3discord, or deploy the published Docker image; the README links installation, DigitalOcean Droplet and OpenAI token guides under detailed_guides/.

How it compares

The provided facts name no competing projects or paid products that GPTDiscord replaces, only dependencies and reference points such as E2B, Qdrant, Pinecone, Wolfram Alpha, Google, DALL-E and the ChatGPT web interface it claims feature parity with. On that evidence it stands alone in this registry.

When to use it — and when not to

A self-hoster must run a Discord bot with its own credentials, hold an OpenAI API key, operate a vector database for custom indexes, and rely on E2B for code execution, so it suits teams already comfortable running Python or Docker services. It is a poor fit for anyone wanting a managed hosted product or support outside Discord, and anyone unwilling to carry OpenAI usage costs. The README excerpt is truncated and the topic list is broad; 44 open issues and a migration away from Pinecone suggest active development rather than a settled, low-maintenance deployment.

project readme (upstream, from github) — read inline

GPT Discord

An all-in-one GPT-3 interface for Discord. ChatGPT-style conversations, image generation, AI-moderation, custom indexes/knowledgebase, youtube summarizer, and more!

Docker
PyPi
Build
PyPi version
Latest release
Maintenance
GitHub license
PRs Welcome

Overview

An all-in-one, robust OpenAI Integration for Discord. This bot is on feature parity with ChatGPT web and even does some things slightly better!

We support everything from multi-modality image understanding, code interpretation, advanced data analysis, Q&A on your own documents, internet-connected chat with Wolfram Alpha and Google access, AI-moderation, image generation with DALL-E, and much more!

BOT SETUP SUPPORT AND DEMO SERVER: Join Here

Featuring code execution and environment manipulation by E2B

We are migrating towards using QDRANT as our vector database backing, we are moving away from pinecone. Qdrant is an excellent vector database choice, and in fact the best one that we've tested and used so far.

Overview of Capabilities

Overview of Features

Table of Contents

Screenshots

Multi-Modality

Internet-connected chat (Google + Wolfram + Link Crawling)

Code Interpreter / Advanced Data Analysis

Custom indexing and Document Q&A

Recent Notable Updates

  • Multi-modality + Drawing - GPTDiscord now supports images sent to the bot during a conversation made with /gpt converse, and the bot can draw images for you and work with you on them!

  • GPT-4-Vision support, GPT-4-Turbo, DALLE-3 Support - Assistant support also coming soon!

  • Code Interpreter / Advanced Data Analysis - Just like ChatGPT, GPTDiscord now has a fully-fledged code execution environment. You can work with GPT to execute your code in an isolated environment, with the ability to even install Python and system packages, and access the internet from the execution environment.

  • Drag And Drop Document Chat - Chat with your documents by simply dragging and dropping files, or even links into discord chat! /index chat

  • Internet-connected Chat! - Chat with an instance of GPT3.5 or GPT-4 that's connected to Google and Wolfram Alpha and can browse and access links that you send it!

Features

  • Multi-modal with image understanding, you can generate images with DALL-E within multi-modal conversations!
  • Code Interpreter / Advanced Data Analysis
  • Long-term, permanent conversations with GPT models
  • Use your own files, PDFs, text files, websites, Discord channel content as context when asking GPT questions!
  • Internet-connected chatting with GPT, connected to Google, Wolfram Alpha, and a web crawler
  • Generate DALL-E AI images and even optimize them right in Discord
  • Translate text with DeepL.
  • Moderate your server automatically with AI!
  • Auto-retry on API errors - Automatically resend failed requests silently to ensure a seamless experience
  • Set context-based pre-instructions per user and per channel
  • Ability to redo, edit your conversation messages while chatting with GPT
  • ShareGPT integration to share your conversations
  • Tag your bot in chat, and it'll respond!
  • Async and fault-tolerant, can handle hundreds of users at once, if the upstream API permits!
  • Change and view model parameters such as temperature, top_p, and more directly within Discord.
  • Tracks token usage automatically
  • Automatic pagination and Discord support. The bot will automatically send very long messages as multiple messages and is able to send Discord code blocks and emoji, gifs, etc.
  • A low usage mode, use a command to automatically switch to a cheaper and faster model to conserve your tokens during times of peak usage.
  • Prints debug to a channel of your choice, so you can view the raw response JSON
  • Ability to specify a limit to how long a conversation can be with the bot, to conserve your tokens.

Commands

These commands are grouped, so each group has a prefix, but you can easily tab complete the command without the prefix. For example, for /gpt ask, if you type /ask and press tab, it'll show up too.

/help - Display help text for the bot

(Chat)GPT Commands

  • /gpt ask Ask the GPT Davinci 003 model a question. Optional overrides available.
  • /gpt edit Use the bot to edit text using the given instructions for how to do it, currently an alpha OpenAI feature so results might vary. Editing is currently free.
  • /gpt converse - Start a conversation with the bot, like ChatGPT. Also use the option use_threads:False to start a conversation in a full Discord channel!
  • /gpt end - End a conversation with the bot.
  • /gpt instruction mode: type: - The commands let you set a system instruction for 3.5-turbo and gpt4 or just prepending text for Davinci and older models.

Code Interpreter // Advanced Data Analysis Commands

  • /code chat - Start a code interpreter chat with GPT. You can type end to end the conversation.

Search & Internet Commands

  • /internet search: scope: nodes: - Search the internet with GPT assistance!
  • /internet chat search_scope: model: - Start an internet-connected chat with GPT, connected to Google and Wolfram.

Custom Indexes Commands

  • /index add file: or link: - Use a document or use a link to create/add to your indexes.
  • /index query query: nodes: response_mode: - Query your current index for a given prompt. GPT will answer based on your current document/index.
  • `/index load user_

readme truncated — read the full docs on github

Frequently asked questions

Is GPTDiscord free to use?

GPTDiscord is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does GPTDiscord do?

A robust, all-in-one GPT interface for Discord. ChatGPT-style conversations, image generation, AI-moderation, custom indexes/knowledgebase, youtube summarizer,

What is GPTDiscord written in?

GPTDiscord is primarily written in Python. Its source is publicly available at https://github.com/Kav-K/GPTDiscord, and it has 1,852 GitHub stars.