Symphony

Symphony is a Slack bot that is basically like ChatGPT but in a Slack Workspace.

Features:

Symphony can do many things!

For example..

• Search the web
• Generate images
• Search URLs
• Peform deep research
• Switch models if needed
• Memory! It can remember things you said in a thread.
• Or..just chatting!

Prerequisites

Before you run this, you will need some things first.

• Python 3.14 (duh!)
• Supabase account (for memory) / API Keys
• OpenAI or any other AI provider URL and API key
• A Slack Bot created
• LinkUp/Search API keys

Quick-Start

1. Clone this repo

git clone https://github.com/Snowflake6413/symphony
cd symphony

2. Copy .env file

cp .env.example .env

(Fill out .env with your keys and params)

3. Install dependencies

pip install .

uv sync 
(if using uv)

4. Create a supabase table

Go to your Supabase project and create a new table on the SQL editor.

• Bot Settings (model switching)

create table bot_settings (
  channel_id text primary key,
  selected_model text not null,
  updated_at timestamp with time zone default timezone('utc'::text, now()) not null
);

• Chat Memory

create table chat_mem (
  id bigint generated by default as identity primary key,
  channel_id text not null,
  thread_ts text not null,
  user_name text,
  role text not null,
  content text not null,
  created_at timestamp with time zone default timezone('utc'::text, now()) not null
);
create index chat_mem_thread_ts_idx on chat_mem (thread_ts);

5. Run it

python app.py

Usage

Once the bot is running, you can invite it to your personal channel and chat with it.

• Mention it to have a chat.
• Run "/symphony-help" to see more commands.
• Switch models with "/model".

License

This repo is licensed under the MIT license. See for more info.