seratch/ChatGPT-in-Slack

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

ChatGPT‑in‑Slack

What it is – An open‑source Slack app that lets you talk to OpenAI’s ChatGPT (and DALL‑E 3) directly from Slack. It works in three ways: in a channel thread, in a 1‑on‑1 DM, or via a Home‑tab modal. The bot keeps the conversation context inside a thread, so you can refine prompts just like on the ChatGPT website.

Key features

  • Threaded conversations – Mention the bot once to start a thread; subsequent messages are automatically sent to ChatGPT, preserving context.
  • Private DM support – Ask the bot privately without needing a mention.
  • Home‑tab UI – Quick‑access dialogs for proofreading, free‑form prompts, and image generation (DALL‑E 3) that work on mobile.
  • Configurable OpenAI settings – Model, temperature, system prompt, language translation, markdown conversion, redaction, and image‑file sharing can be toggled via environment variables.
  • Docker & Socket Mode – Deployable behind your own firewall; uses Slack’s Socket Mode so no public URL is required.
  • Azure OpenAI compatibility – Optional environment variables let you point the app at Azure’s OpenAI endpoint.
  • Function‑calling demo – Experimental support for OpenAI function calling via a test module.

How to run it locally

  1. Create a Slack app from the provided manifest-dev.yml and install it in your workspace.
  2. Set the required env vars (SLACK_APP_TOKEN, SLACK_BOT_TOKEN, OPENAI_API_KEY). Optional vars let you pick a model, temperature, etc.
  3. Install dependencies (pip install -r requirements.txt) and start the bot (python main.py).
  4. (Optional) copy .env.example to .env and edit the values for easier local development.

Deploying for a company

  • Build the supplied Dockerfile. The container runs in Socket Mode, so it only needs outbound connections to Slack and OpenAI.
  • Because the code is MIT‑licensed, you can host it on your own infrastructure, ensuring that any confidential data stays within your control.

Typical use cases

  • Drafting or polishing emails, reports, or any text directly from Slack.
  • Quickly generating images with DALL‑E 3 without leaving the chat.
  • Getting instant code snippets, explanations, or brainstorming ideas while collaborating.
  • Providing a shared “AI assistant” that team members can reference in public threads.

Related projects

  • iwamot/collmbo – a fork that adds support for other LLM providers via LiteLLM.

License – MIT.

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
    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
    V-know/ChatGPT-Telegram-Bot

    A Telegram bot that integrates OpenAI and Azure OpenAI to provide streaming text and DALL-E 3 image generation with built-in user management.

  • Project
    Niek/chatgpt-web

    ChatGPT‑web is an open‑source, single‑page web UI that lets you chat with any OpenAI‑compatible LLM (OpenAI, Anthropic, Gemini, etc.). Conversations are stored locally, the app supports voice I/O, image generation, streaming responses, and can be run in the browser, via Docker, or packaged as a native desktop app.