Setup

Get Dash running on your machine with a synthetic SaaS dataset (~900 customers, two years of data) so you have something concrete to ask about.

Prerequisites

Docker Desktop (install)
OpenAI API key (get one)

Manual
Agentic

Clone and configure

git clone https://github.com/agno-agi/dash && cd dash
cp example.env .env

Open .env and set OPENAI_API_KEY. Everything else has sensible defaults.

Start Dash

docker compose up -d --build

First run builds the Dash image and boots a local Postgres. Takes a minute or two. Subsequent starts come up in seconds.

Load sample data and knowledge

docker exec -it dash-api python scripts/generate_data.py
docker exec -it dash-api python scripts/load_knowledge.py

generate_data.py seeds the SaaS dataset (customers, subscriptions, invoices, usage, support tickets). load_knowledge.py loads the table metadata, query patterns, and business rules in knowledge/.

Verify it's running

curl http://localhost:8000/health

Expect {"status":"ok"}. Connection refused means the container is still starting. Check docker compose logs -f dash-api and wait for the Agno banner.

If you have a coding agent like Claude Code or Codex, paste this prompt into a fresh session in an empty directory. The agent clones the repo, starts Dash, loads the dataset, and verifies it’s running.The prompt below never asks the agent to read or transmit your API key. The agent opens .env for you to edit, then waits for you to confirm before continuing.

Set up Dash locally for me.

Steps:
Clone https://github.com/agno-agi/dash into the current directory and cd into it.
Copy example.env to .env. Open .env in the user's editor (or print the path and tell them to open it). Tell the user: "Set OPENAI_API_KEY in .env, save the file, then tell me to continue." Wait for confirmation before proceeding. Do not ask the user to paste the key into this chat. Do not read the key from .env or print its value at any point.
Check that Docker Desktop is running (`docker info`). If not, tell me to start it and stop.
Run `docker compose up -d --build`. Stream the output so I can see progress.
Poll `curl -s http://localhost:8000/health` every 3 seconds for up to 60 seconds. Proceed once it returns `{"status":"ok"}`.
Run `docker exec -it dash-api python scripts/generate_data.py` to seed the SaaS dataset.
Run `docker exec -it dash-api python scripts/load_knowledge.py` to load table metadata, query patterns, and business rules.
Print next steps: open os.agno.com, Add OS → Local → http://localhost:8000.

If any step fails, stop and show me the error. Don't try to fix it on your own.

Connect to AgentOS UI

Open os.agno.com and log in. Click Add OS, choose Local, enter http://localhost:8000, click Connect. Try a question:

“What’s our current MRR?”

“Which plan has the highest churn rate?”

“Show me revenue trends by plan over the last 6 months.”

Dash routes through its team. The Analyst introspects the schema and writes read-only SQL. The Engineer builds reusable views in the agent-managed dash schema. The Leader coordinates and answers.

What you have now

Component	Detail
Dash team	Analyst (read-only `public`), Engineer (writes to `dash` schema), Leader (coordinator)
`public` schema	Synthetic SaaS data: `customers`, `subscriptions`, `plan_changes`, `invoices`, `usage_metrics`, `support_tickets`
`dash` schema	Agent-managed views and summary tables. Empty until the Engineer builds something.
Knowledge	Table metadata, query patterns, and business rules from `knowledge/`. Powers the Analyst’s grounding.
Learnings	Error patterns and fixes captured by Agno’s Learning Machine as Dash works.

For the architecture deep dive (six layers of context, self-learning loop, dual schema enforcement), see What is Dash?.

Connect to Slack →

Welcome

Tutorials

Runtime

Demo OS

Prerequisites

Connect to AgentOS UI

What you have now

Next

Welcome

Tutorials

Runtime

Demo OS

​Prerequisites

​Connect to AgentOS UI

​What you have now

​Next

Prerequisites

Connect to AgentOS UI

What you have now

Next