Planet Ingres

 Google brings the power of Chrome DevTools to AI coding assistants with its Chrome DevTools Model Context Protocol server, now in public preview. 

https://www.i-programmer.info/news/90-tools/18416-chrome-devtools-to-benefit-from-mcp.html

 Google's AI Studio can now generate Angular applications. Add the Web Codegen Scorer tool on top and you get a pretty solid Angular development platform.

https://www.i-programmer.info/news/167-javascript/18414-google-ai-studio-does-angular.html

 IBM has launched Granite 4.0, the next generation of open-source, small but efficient, IBM language models, together with Granite-Docling, the next gen document format converter.

https://www.i-programmer.info/news/80-java/18409-ibm-launches-granite-version-40-and-granite-docling-.html

 New options are now available for Jules, Google's coding Agent - a CLI and an API. We covered the release of Jules back in August, see Google Jules Coding Assistant Now Available. To cut a long story short, we found that Jules is:

https://www.i-programmer.info/news/105-artificial-intelligence/18404-jules-coding-agent-upgraded.html

 It's been some years since we first looked at Qodana, the solid SAST tool from JetBrains. Let's find out what's new in its latest release, Qodana 2025.2.

https://www.i-programmer.info/news/90-tools/18398-qodana-revisited-.html

 ChartDB strikes back with a database agent that auto-magically draws database schemas for you.

Last February in Database Diagramming With ChartDB we looked at ChartDB as an open-source database diagrams editor that can be self-hosted or used in the Cloud which could:

https://www.i-programmer.info/news/90-tools/18391-chartdb-the-erd-agent.html

 PostgreSQL 18 was released on September 25, boosting a many great features. If you check out the official release statement you'll find that there's a lot to digest, so we'll focus on just a few key features.

https://www.i-programmer.info/news/84-database/18383-postgresql-18-released-whats-new.html

 Google has released a small, specialized, but powerful model that can run on low resource devices.

EmbeddingGemma is a new open embedding model that delivers value for money for its size. Based on the Gemma 3 architecture, it is trained on 100+ languages and is small enough to run on less than 200MB of RAM with quantization.

https://www.i-programmer.info/news/105-artificial-intelligence/18358-google-releases-embeddinggemma-state-of-the-art-on-device-embedding.html

 Google's open source MCP server that allows AI agents to interact with SQL databases.

The difference betweenm it and other MCP to SQL servers is that it takes out complexities such as connection pooling, authentication and observability so that the developer can solely focus on implementing the logic of his Agents

https://www.i-programmer.info/news/89-net/18364-googles-mcp-toolbox-for-databases.html

 Simply referred to as "LLM Visualization" this web site with interactive and intuitable graphics explains how an LLM actually works.

https://www.i-programmer.info/news/105-artificial-intelligence/18393-visualize-the-inner-workings-of-an-llm.html