seratch/ChatGPT-in-Slack

Swift demonstration of how to build a Slack app that enables end-users to interact with a ChatGPT bot

What it solves

This project provides a way to integrate ChatGPT and DALL-E 3 into a Slack workspace, allowing users to interact with AI models directly within their communication tool. It eliminates the need to switch between Slack and the OpenAI web interface, facilitating better collaboration on writing, planning, and proofreading tasks.

How it works

The app acts as a bridge between Slack and the OpenAI API. It supports three primary interaction interfaces:

  • Channel Threads: Users can mention the bot to start a conversation, and the bot maintains context within that specific thread.
  • Direct Messages: Users can have private 1:1 conversations with the bot.
  • Home Tab: A dedicated space for configuring API keys, model settings, and using quick-access tools like a proofreader or a general prompt sender.

Who it’s for

Individuals and teams using Slack who want to leverage LLMs for productivity, as well as corporate environments that require self-hosting the app on their own infrastructure for data confidentiality.

Highlights

  • Contextual Memory: Remembers previous messages within the same Slack thread.
  • ** uma DALL-E 3 Integration**: Supports image generation via prompts.
  • Flexible Deployment: Can be run locally or deployed via Docker using Socket Mode, removing the requirement for a public URL.
  • ** uma Customization**: Supports system prompts (priming instructions) to define the bot's purpose, such as turning it into a dedicated proofreader.
  • Azure OpenAI Support: Compatible with Azure OpenAI v1 API.

Related

  • Project
    CopilotKit/channels-sdk

    An SDK that connects AI agents to Slack, Microsoft Teams, and Discord, enabling native interactive UI and human-in-the-loop approvals.

  • Project
    CopilotKit/OpenTag

    OpenTag is an open‑source, self‑hosted AI assistant that connects a LangGraph‑based Python agent to Slack and Microsoft Teams via CopilotKit’s managed Channels. It can ingest files, run live web research, create Linear or Notion items (with approval), and render native Slack UI (charts, tables, cards). Deploy with Railway or AWS, customize prompts, tools, and UI by editing a few files, and run the stack with `pnpm dev` after setting a few environment variables.

  • Project
    korotovsky/slack-mcp-server

    An MCP server that enables AI models to interact with Slack workspaces, allowing them to read, search, and manage messages, users, and channels.

  • Dispatch
    CopilotKit Channels SDK Open-Source Release Enables Any AI Agent on Slack, Teams, Discord, and More

    CopilotKit released the open-source Channels SDK, letting developers attach any AG‑UI‑compatible AI agent to Slack, Microsoft Teams, Discord, Telegram and other chat platforms with native interactive UI.

  • Project
    yincongcyincong/MuseBot

    MuseBot is an open‑source Go bot that connects Telegram, Discord, Slack, Lark, DingTalk, Enterprise WeChat, QQ and WeChat to a wide range of LLM APIs (OpenAI, DeepSeek, Gemini, OpenRouter, etc.). It streams AI replies, supports image/voice input, function calls, RAG, admin UI, metrics and cron jobs, and can be run locally or via Docker.