Tatsoft Releases FrameworX 10.1.5 with Local AI and Knowledge Graph Features

Jul 7, 2026
Tatsoft has introduced FrameworX 10.1.5, adding full AI integration across engineering and operations, a live industrial Knowledge Graph, and a local AI service that runs entirely on-site behind the customer firewall.

Tatsoft has released FrameworX 10.1.5, its latest update to the unified SCADA, HMI, and Historian platform for industrial automation, announced in a press release. The release introduces complete AI integration across engineering and operations environments, an industrial ontology layer with a live Knowledge Graph, and a local AI service that runs fully on the customer’s server without cloud dependency.

In the FrameworX Designer, an AI assistant connects through eighteen native MCP tools to generate tags, alarms, displays, device links, and scripts from plain language inputs. During runtime, users can query process data, historian records, and active alarms through an AI Chat interface. The AI system is optimized for Anthropic Claude and supports other MCP-compatible models.

FrameworX 10.1.5 also includes an ontology layer following ISA-88, ISA-95, and OPC-UA standards, enabling semantic organization of assets and devices. A one-click Knowledge Graph report produces a visual hierarchy of assets, and the new TKnowledgeGraph control displays these relationships in WPF and HTML5 clients. Additional improvements include new database connectors for MongoDB and QuestDB, OIDC and OAuth2 Single Sign-On, REST APIs, and updated runtime support for .NET 10 LTS.

The update is available now as a free upgrade for existing FrameworX 10.x users with no migration required.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Industrial AI Weekly or Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Industrial AI Weekly

The latest advancements in smart manufacturing, predictive maintenance, AI-driven quality control, supply chain & more.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.