As a Java developer, integrating Large Language Models (LLMs) into applications is becoming a core requirement. While cloud APIs like Google Gemini, Anthropic’s Claude, or OpenAI’s GPT are convenient, running models locally on my machine offers lower latency, zero API costs, privacy, and full control over system telemetry. I can even run models disconnected from the internet, when I’m travelling in a train or a plane!

When Google released Gemma 4, I wanted to find the best way to run Gemma 4 locally on my Apple Silicon Mac (equipped with 48GB of unified RAM) and consume it seamlessly from Java 25 using LangChain4j.

A few weeks ago, I wrote about building the Antigravity Brain Visualizer: a tool to parse raw JSONL transcript logs from Antigravity AI agent sessions and render them into an interactive web interface with proportional timelines and sequence groupings.

While visual timeline scrubbing and sequence filtering made it easier to inspect what an agent did, diagnosing complex tool failures or creating preventative guardrails still required manual investigation:

• Why did a tool call fail at step #38?
• What sequence of events led up to a specific error?
• Could I automatically turn a failure pattern into an Agent Skill to prevent Antigravity from repeating the mistake?

To address these questions directly within the application, I built the Interactive Session Assistant in v0.4.1 of the Antigravity Brain Visualizer. It transforms the visualizer from a passive log viewer into an interactive diagnostic co-pilot.

When AI coding agents tackle complex tasks, they often waste time making the same mistakes, running into environment quirks, or retrying failed approaches before finding something that works. If an agent encounters a domain-specific trap in one session, that lesson is lost when the next session starts, forcing the agent to repeat the exact same trial-and-error cycle.

I built the Open Reasoning Format (ORF) to fix this. ORF is a lightweight, file-based specification that lets AI agents record and retrieve operational learnings across sessions. With access to playbooks from previous runs, agents facing similar problems can skip known dead ends, reach working solutions faster, and use about half the steps (and tokens).

I constantly use a text editor to jot ideas, draft blog posts, or collate documents, but my usual options always felt a bit off. TextEdit is too bare-bones and defaults to a tiny font I can barely read. MacVim takes a few seconds too long to load. VS Code requires me to dismiss plugin updates and changelogs before I can even start typing.

I realized I didn’t want another bloated app from a big tech company. I wanted a personal tool tailored exactly to my workflow.

For the past few weeks, a lot has been written and said about Loop Engineering, and we’re seeing an explosion of Agent Skills out there for various tasks. These concepts are trendy, but how do they actually translate into day-to-day productivity?

Today, I want to testify with a concrete use case where skills and loops helped me become significantly more productive: authoring Google Codelabs.

About Codelabs

For those who might not be familiar, Google Codelabs are guided, hands-on coding tutorials that walk developers step-by-step through building an application, integrating an API, or learning a new technology. They are great educational resources, but crafting a high-quality one is far from trivial, and takes time.

Google just announced the launch of some new image and video models: Nano Banana 2 Lite (the fastest, most cost-efficient Gemini Image model yet) and Gemini Omni Flash for high-quality video and conversational editing. You can read all about the announcement on the Google Blog.

As soon as I saw the news, I couldn’t wait to get my hands dirty. I wanted to see how easy it would be to generate images and videos using the Gemini Interactions API Java SDK.

The Google Gemini Interactions API is now generally available (GA). It provides a unified interface for interacting with Gemini models and agents. You can read the official announcement on the Google Blog, and if you are using Python, Philipp Schmid published a helpful developer guide to get started.

For Java developers, the Gemini Interactions API SDK for Java is gearing up for its stable release with the availability of v1.0.0-RC1. Here is a look at what is new in this release candidate.

My daughter’s French Bac de Philosophie (philosophy baccalaureate) is tomorrow. Preparing for this examination usually involves reviewing handwritten flashcards, printed handouts, and paper notes.

Reviewing these concepts, authors, works, and quotes systematically is a pain. My daughter asked me for a digital tool to help her study, as she knew I had already helped her younger sister with similar tools for learning or revising her lessons.

I built an interactive study application. What started as a single-evening project became a web application, written in a mere couple hours of vibe coding in Google AI Studio and Gemini.

When working with autonomous AI agents like Antigravity, understanding what they are doing in the background can be difficult. The agents construct reasoning chains, dispatch background tasks, and execute system commands over long sessions. All of this is recorded in detailed JSONL transcript files. Reading raw JSONL is inefficient, so I built the Antigravity Brain Visualizer to parse and render these transcripts into an interactive interface.

Antigravity CLI allows you to customize both the terminal window title and the bottom status line. This is done by passing a JSON payload of the current agent state to external shell scripts via standard input.

In this post, I will explain how I set up my environment, the specific scripts I use, and how to configure the CLI to load them.

The Principle

Both the title and the status line operate on the same principle: