Tater is a local AI assistant powered by Hydra and local AI models, giving you a powerful set of AI-driven tools. It includes a WebUI for setup and private chats, and works across Discord, Home Assistant, HomeKit, IRC, macOS, Matrix, Telegram, and even the OG Xbox via XBMC4Xbox

Main website: taterassistant.com

Tater is powered by Hydra, a four-head system:

• Astraeus - sees
• Thanatos - executes
• Minos - judges
• Hermes - speaks

Loop: plan -> execute -> judge -> respond.

Chat turns stay lightweight: Astraeus handles conversational awareness, while Thanatos/Minos/Hermes only engage when execution is needed.

Model routing:

• Base model settings (Hydra LLM Host, Hydra LLM Port, Hydra LLM Model) define AI Calls.
• You can add multiple Base servers; regular AI calls rotate round-robin.
• Beast Mode off: all heads use the Base server pool.
• Beast Mode on: AI Calls still use the Base pool, while Chat/Astraeus/Thanatos/Minos/Hermes each use their own model settings.

Tater uses Tater Shop to manage:

• Verbas
• Portals
• Cores

This repository no longer keeps static lists of those modules in the README. Instead, catalogs, versions, metadata, and update paths are managed in:

👉 https://github.com/TaterTotterson/Tater_Shop

From the WebUI, use:

• Verba Manager
• Portal Manager
• Core Manager

Each manager supports browse/install/update/remove and startup restore for enabled items that are missing on disk.

Some Portals are paired with companion repos/apps that complete the end-user integration:

Note:

• Tater currently recommends using qwen3-coder-next, qwen3-next-80b, gpt-oss-120b, qwen3-coder-30b or Gemma3-27b

Tater is available in the Unraid Community Apps store.

You can install both:

• Tater
• Redis Stack

directly from the Unraid App Store with a one-click template.

Unraid note:

• Add container path mappings for /app/agent_lab and /app/.runtime to persistent shares (for example /mnt/user/appdata/tater/agent_lab and /mnt/user/appdata/tater/runtime) so you don’t lose Agent Lab data or Redis setup config during container updates.
• Also set TZ and map /etc/localtime + /etc/timezone if you want local time inside the container.

A dedicated Home Assistant add-on repository is available here:

https://github.com/TaterTotterson/hassio-addons-tater

Click the button below to add the repository to Home Assistant:

Once added, the following add-ons will appear in the Home Assistant Add-on Store:

• Redis Stack – required for Tater memory, Verbas, and automations
• Tater AI Assistant – the main Tater service

1. Install and start Redis Stack
2. Install Tater AI Assistant
3. Configure your LLM and Redis settings in the Tater add-on
4. Start Tater

This is the recommended setup for most users and provides the smoothest experience.

• Python 3.11
• Redis-Stack
• A local LLM runtime (such as Ollama, LocalAI, LM Studio, or Lemonade)
• Docker (optional, for containerized deployment)

Install Redis Stack from the official Redis APT repository:

sudo apt-get install -y lsb-release curl gpg
curl -fsSL https://packages.redis.io/gpg | sudo gpg --dearmor -o /usr/share/keyrings/redis-archive-keyring.gpg
sudo chmod 644 /usr/share/keyrings/redis-archive-keyring.gpg
echo "deb [signed-by=/usr/share/keyrings/redis-archive-keyring.gpg] https://packages.redis.io/deb $(lsb_release -cs) main" | sudo tee /etc/apt/sources.list.d/redis.list
sudo apt-get update
sudo apt-get install -y redis-stack-server
sudo systemctl enable redis-stack-server
sudo systemctl start redis-stack-server

Verify Redis is up:

redis-cli ping

Expected output:

PONG

1. Clone the Repository

git clone https://github.com/TaterTotterson/Tater.git

2. Navigate to the Project Directory

cd Tater

Note:

• Run Tater inside a Python virtual environment so dependencies stay isolated and easy to manage (recommended). Quickstart:

  python -m venv .venv
  source .venv/bin/activate

3. Install Dependencies

Using pip, run:

pip install -r requirements.txt

4. First-Run Redis Setup

You no longer configure Redis in .env.

Start TaterOS, open the WebUI, and a Redis Setup popup will appear automatically if Redis is not configured yet. Enter:

• Redis host
• Redis port
• Optional auth (username / password)
• Optional TLS settings

Those connection settings are saved locally by TaterOS for future boots.

After starting TaterOS, configure your local LLM endpoint in Settings:

• Hydra LLM Host
• Hydra LLM Port
• Hydra LLM Model
• Optional: add more Base servers for round-robin regular AI calls.
• Optional: enable Beast Mode and set per-head model settings for Chat/Astraeus/Thanatos/Minos/Hermes.

Those values are stored in Redis and used by Hydra at runtime.

5. Run the Web UI

Run the TaterOS backend/frontend (FastAPI + static HTML/CSS/JS):

uvicorn tateros_app:app --host 0.0.0.0 --port 8501 --reload --no-access-log

Docker-style launcher (also disables access logs by default):

sh run_ui.sh

Then open:

http://127.0.0.1:8501

Pull the prebuilt image with the following command:

docker pull ghcr.io/tatertotterson/tater:latest

Redis settings are configured in the WebUI setup popup (not via .env).

Important for Docker persistence:

• Add a path mapping for /app/agent_lab (container) -> /mnt/user/appdata/tater/agent_lab (host example).
• Without this mapping, data in /agent_lab (logs/downloads/documents/workspace) can be lost on container rebuilds/updates.
• Add a path mapping for /app/.runtime (container) -> /mnt/user/appdata/tater/runtime (host example).
• Without this mapping, Redis setup popup settings can be lost on container rebuilds/updates.

Example: local setup

docker run -d --name tater_webui \
  -p 8501:8501 \
  -p 8787:8787 \
  -p 8788:8788 \
  -p 8789:8789 \
  -p 8790:8790 \
  -e TZ=America/Chicago \
  -v /etc/localtime:/etc/localtime:ro \
  -v /etc/timezone:/etc/timezone:ro \
  -v /agent_lab:/app/agent_lab \
  -v /tater_runtime:/app/.runtime \
  ghcr.io/tatertotterson/tater:latest

After the container is running, open TaterOS, complete the Redis setup popup, then configure local LLM endpoint/model in Settings:

• Hydra LLM Host
• Hydra LLM Port
• Hydra LLM Model
• Optional: add more Base servers for round-robin regular AI calls.
• Optional: enable Beast Mode and set per-head model settings for Chat/Astraeus/Thanatos/Minos/Hermes.

Tip: Redis setup popup config is stored at /app/.runtime/redis_connection.json inside the container.

Optional: if you want a custom config file location, set TATER_REDIS_CONFIG_PATH and mount that target path from the host.

Access-log note: run_ui.sh now starts Uvicorn with --no-access-log to suppress per-request lines.

Once the container is running, open your browser and navigate to:

http://localhost:8501