update
May 28, 2026
By Teun
Data Formulator 0.7 adds AI analytics tools for enterprise data
Data Formulator 0.7 is an open-source AI-powered data analytics system for enterprise teams. The release adds reusable Data Connectors, context-aware agents, and an interactive workspace for exploring and refining analyses across fragmented data sources.
Data Formulator 0.7 is an open-source AI-powered system for enterprise data analytics that aims to make fragmented data easier to work with. The release combines reusable data connections, context-aware agents, and an interactive workspace for iterating on charts and analysis, according to the project announcement.
The main new feature is Data Connectors, which support governed, reusable connections across databases, warehouses, BI systems, object stores, and local files. According to the project, the connectors include authentication, persistent connections, previews, metadata, and a unified workspace model. The goal is to reduce integration work for platform teams and avoid repeated manual file uploads.
⚡ New to this?
This matters because many companies keep data in different systems, which makes analysis slow and hard to reproduce. Data Formulator 0.7 tries to solve that by combining data connections, AI agents, and a shared workspace so people can explore data without starting from scratch each time.
A “context-aware” agent is an AI assistant that can see more than a single chat prompt; it can use the connected data, charts, and prior steps in the analysis. That is useful for teams that need traceable work, not just one-off answers.
🦞 OpenClaw angle
If you build self-hosted AI analytics tools, treat persistent workspace state as a core feature, not an add-on. Store connected sources, loaded tables, chart history, and intermediate outputs so agents can branch and resume analysis without losing context.
If you manage internal data access, model your connectors around reusable, governed connections with authentication, metadata, and previews. Also have agents ask clarifying questions before running expensive or irreversible steps, and keep generated code or transformation steps attached to each result for later review.
The release comes as enterprise teams are increasingly using AI for analytics while dealing with data spread across many systems. Before analysis can begin, teams often need to set up governed connections, prepare metadata, manage permissions, and build workflows that combine and reshape data across sources, the project said. Data Formulator 0.7 is meant to bring those pieces into a single workspace.
Context-aware agents sit at the center of the system. Unlike a single prompt in a chat window, these agents can access the full analysis workspace, including connected data sources, loaded tables, prior charts, and the user’s objective. They use tools rather than text alone, and can inspect data, write and run code in an isolated environment, generate chart specifications, and explain results while showing intermediate steps.
When a request is unclear, the agent asks clarifying questions before moving ahead. According to the project, that helps the system handle longer analytical workflows such as aligning analysis with a user’s goal, preparing and transforming data, suggesting follow-up questions, generating tables and charts in batch, and producing verifiable code for each result.
Data Formulator also includes a multimodal interface built for iterative analysis. Users work with agents through the Data Thread, a structured chat that records every question, intermediate finding, and chart during the process. The project says this keeps long sessions navigable, letting users return to earlier steps, branch into alternate analyses, and compare results side by side without losing context.
The interface also includes an interactive canvas for editing charts directly. Users can refine visualizations on the canvas or describe changes in natural language, and the agent can adjust labels, annotations, layout, color, and emphasis. Analysts can also generate reports and share findings with others.
The project said teams building analytics workflows for enterprise data can use Data Formulator as a foundation for adapting these capabilities to their own systems and requirements. A demo and GitHub repository are available through the project’s release materials.
