OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Data Agents

Dash

Dash is an open-source Python data agent that answers natural-language questions by grounding SQL generation and result interpretation in data schemas, business rules, known queries, institutional references, learned fixes, and live schema context.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Dash — OpenViST project profile in Data Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Dash when building or exploring an agent that needs to answer business-data questions with context beyond database schemas, such as definitions, query examples, and learned SQL fixes.

Who it is for

  • Developers building data-question-answering agents.
  • Teams exploring natural-language access to business metrics and text-to-SQL workflows.
  • Builders who want to expose a data agent through a terminal, Slack, or an AgentOS web UI.

Documented uses

  • Ask questions about business data in natural language and receive interpreted answers.
  • Ground SQL generation in schema details, metric definitions, known query patterns, and other contextual knowledge.
  • Generate sample data and load knowledge to explore the project locally.
  • Use a self-learning loop that records error patterns and fixes for later queries.
Before you choose

Requirements & limits

The project is an open-source public GitHub repository under the Apache-2.0 license. Its local quick start requires an OpenAI API key; the documented AgentOS web UI flow requires login.

  • Local setup uses Docker Compose and an OpenAI API key.
  • Dash separates an analyst role with read-only access to public data from an engineer role that writes within the agent-managed dash schema.
  • The README documents six grounding layers: table usage, human annotations, query patterns, institutional knowledge, learnings, and runtime schema context.
  • Slack is described as an optional interface; terminal and AgentOS web UI access are also described.
  • The documented local quick start generates sample data rather than specifying a general-purpose procedure for connecting an arbitrary existing dataset.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Start Dash locally with sample data

Bring up the local Dash service and load the sample dataset and knowledge files.

Before you start

  • Git
  • Docker Compose
  • An OpenAI API key

Steps

  1. Clone the Dash repository and change into its directory.

  2. Copy example.env to .env and add the OPENAI_API_KEY value.

  3. Start the system with the command below.

    Documented command
    docker compose up -d --build

  4. Run the command below, then the command below.

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

  5. Use http://localhost:8000/docs to confirm the service is running; to use the web UI, connect AgentOS to http://localhost:8000 as a Local OS and select Connect.

Expected outcome

A local Dash service with generated sample data and loaded knowledge, accessible through its API documentation and connectable to AgentOS.

Guide limitations

  • The README’s example questions use a SaaS metrics dataset; the guide does not describe loading a separate production database.
  • The AgentOS web UI connection instructions require logging in to AgentOS.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
agno-agi/dash · Official homepage title · retained in its source language
How we review sourcesSuggest a correction