OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Ryoma

Ryoma is an Apache-2.0-licensed Python framework for building AI agents for data analysis, data engineering and visualization. Its documented example connects an agent to PostgreSQL so it can translate a natural-language question into a SQL query and return database results.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Ryoma — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Ryoma when building a Python-based data agent, especially when a workflow should connect a language model to a database or when a Reflex-based local interface is useful.

Who it is for

  • Python developers building AI-assisted data workflows.
  • Data practitioners who want to query a PostgreSQL database through a language-model agent.
  • Teams exploring a local web interface for interacting with data and AI models.

Documented uses

  • Build a data-analysis agent to explore and interpret datasets.
  • Create an agent that assists with data engineering tasks.
  • Develop an agent for data visualization.
  • Ask a database question in natural language and have an agent prepare and run a SQL query.
Before you choose

Requirements & limits

Ryoma is published under the Apache-2.0 license. The documented installation uses pip.

  • The README's concrete agent example uses PostgreSQL and demonstrates a tool call that executes SQL.
  • Model-provider support requires the corresponding Python packages and, for providers that use credentials, the relevant environment variables.
  • The project lists LangChain, Reflex, Apache Arrow, Jupyter AI Magics, Amundsen, Ibis and Feast in its stack.
  • The package is installed as ryoma_ai; the optional Snowflake extra is documented as ryoma_ai[snowflake].

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

Set up Ryoma Lab

Configure and start the Reflex-based Ryoma Lab interface locally.

Before you start

  • Install the Ryoma package and its dependencies in a Python project.
  • Create an rxconfig.py file in the project.

Steps

  1. Add the documented Reflex configuration to rxconfig.py, setting the app name to ryoma_lab and the log level to INFO.

  2. Run ryoma_lab run from the project.

  3. Open the local interface at http://localhost:3000.

Expected outcome

Ryoma Lab is available through a local web interface.

Guide limitations

  • The documented steps describe starting the interface, not connecting a specific data source or model inside it.
Documentation 1 ↗
Evidence and transparency

Sources & review

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