dataagent

DataFoundry is an open-source AI workbench for data analysis, unifying data sources, knowledge, tools, and agent runtime into a governed workspace for interacti

What is dataagent?

DataFoundry is an open-source AI workbench for data analysis, unifying data sources, knowledge, tools, and agent runtime into a governed workspace for interactive analytics.

Overview of dataagent

What it is

DataFoundry is an enterprise-grade, open-source AI workbench designed for data analysis. It unifies data sources, knowledge, tools, and agent runtime into a governed workspace. The tool reads business definitions from a semantic layer, runs complex multi-table and multi-step analysis within read-only boundaries, and makes every step auditable and replayable. It turns a single question into a trustworthy analysis, addressing concerns around business logic understanding, data mutation, credential security, and verifiability. DataFoundry supports 28 datasource types out of the box, enterprise semantics, self-hosted deployment, multi-model support, and full auditability. Version 0.2.0 introduces branchable concurrent analysis, evidence-first follow-ups, semantic trace, DataLink integration, reusable outputs, and a production-facing web foundation. The tool is available for Linux via a one-click deployment script and for Windows, macOS, and other systems via manual npm commands.

Key features

  • 28 datasource types out of the box — connects to PostgreSQL, MySQL, Snowflake, BigQuery, ClickHouse, MongoDB, Redis, Elasticsearch, and others.
  • Enterprise semantics and context organization — manages schema, metric definitions, and field relationships so terms like 'GMV' resolve to approved definitions.
  • Self-hosted deployment and multi-model support — runs inside your boundary; any OpenAI-compatible provider works (Qwen, DeepSeek, GPT).
  • Safe by default and auditable throughout — read-only queries, credential isolation, field masking, row limits, timeouts; every SQL and tool call is persisted and replayable.
  • Deep optimization for complex data tasks — decomposes, verifies, and converges multi-table, multi-field, long-horizon analysis into trustworthy conclusions.

Use cases

DataFoundry is intended for enterprise teams that need to let AI query databases safely. It is used for multi-table, multi-step analytical queries, natural-language-based data exploration, and generating auditable reports. It is suitable for scenarios where business definitions must be respected, data must not be mutated, and every step must be verifiable after the fact. Common use cases include finance analysis (e.g., GMV tracking), customer retention analysis, and any governed interactive analytics.

Getting started

See the repository README for full instructions. The recommended one-click deploy for Ubuntu/Debian is:bashgit clone https://github.com/datagallery-lab/datafoundry.gitcd datafoundry./deploy.shAfter deploy, open http://127.0.0.1:3000/login, register or sign in, and create an OpenAI-compatible model profile.

License and pricing

The license is Apache-2.0. The project is open source; no pricing is stated.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/datagallery-aidataagent.svg)](https://yunodb.com/tools/datagallery-aidataagent?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/datagallery-aidataagent?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/datagallery-aidataagent.svg" alt="Featured on YunoDB" height="20"></a>