Guillaume Laforge

Fanny Klauk - Informaticienne ingénieuse

22 Oct 2025

My comprehensive guide on building #AI #agents in #Java with the #ADK framework! 🤖☕ I've bundled everything you need to get started: my full article, the video recording at @devoxx.com, a codelab, the slides, an updated template project, and code samples, all in one place.

Guillaume Laforge reposted

@klf37.bsky.social

J'adore TADx. J'adore me creuser les méninges pour identifier les prochains sujets, prendre du temps pour l'organisation avec @wilda.bsky.social , recevoir des speakers talentueux, vous croiser après la conférence et refaire le monde... Mais... Stop ou encore ?

TADx@tadx.bsky.social

En ce moment les meetups et les conférences tech en France ont du mal. #TADx n'y échappe pas et si vous voulez comprendre notre démarche et nos interrogations on vous laisse lire ce blog post : www.tadx.fr/2026-10-09-w... N'hésitez pas à nous faire vos retours 🤗.

tadx.fr TADx a besoin de toi ! 🫵 - TADx Vous l’avez peut-être constaté, mais les conférences et les meetups tirent la langue ces derniers temps 🥵. Pour plusieurs raisons, parfois communes, parfois ...

glaforge.devThe eMudhra CA Compromise: Why Your JVM Is Vulnerable (and How to Fix It Properly)Why browsers are already protected against the October 2026 eMudhra intermediate CA private key compromise while Java installations remain exposed, why deleting emSign from cacerts is not enough, and ...

Fellow #java developers, you are likely affected by the #eMudhras CA compromise. Let's fix your #java and @graalvm.org installations and apps: glaforge.dev/posts/2026/1...

Guillaume Laforge reposted

Gus

@gusthema.bsky.social

We launched a new home for Gemma developer docs at https://gemma.ai 📚💎 Includes a global model selector that adapts code snippets across sizes, one-click Markdown export on every page for local coding agents, and live on-device WebGPU demos in the browser.

Guillaume Laforge reposted

Google Open Source

@opensource.google

This Week in Open Source #19 is live! 🌐✨ 🐚 A2A + MCP from Toronto to your terminal (A2A CLI & a2term) 🧲 Local multimodal search w/ EmbeddingGemma 2 (567MB RAM) 🧩 Live AT Protocol 3D Web Tiles 🐧 35 years of Linux & 2026 State of OSPOs w/ @linuxfoundation.org: goo.gle/twios-19

Just released a new version (v2.1.0) of my #Gemini Interactions #Java API with support for 𝗚𝗲𝗺𝗶𝗻𝗶 𝟰 𝗔𝗿𝗴𝗼𝗻 github.com/glaforge/gem...

You'll see a bunch of cool demos of #Gemini 4 Argon today 😆 I like to use #LLMs to learn new things. @groovy.apache.org released version 6: a big milestone. I asked #antigravity & #Gemini 4 Argon to create an interactive site to learn about the latest features: glaforge.dev/groovy6showc...

You can explore the themes of the release, with live examples running via #GoogleCloud functions & #CloudRun, in the Groovy Web Console. And you can edit the snippets to see the features in action.

groovy-lang.orgThe Apache Groovy programming language - Groovy 6.0 release notes

All the content is based on the @groovy.apache.org release notes: groovy-lang.org/releasenotes...

glaforge.devGetting Started with Google AntigravityEarlier this week, I spoke at the first edition of the Dev With AI conference in Paris, held at the Forum des Images. The event brought together around 500 developers to exchange notes on practical AI...

It was a pleasure to talk at the #DevWithAI conference in Paris, organized by Greg Lhotellier. I spoke about #antigravity to 500 developers, and had very interesting discussions on the impact of #AI on our developer journey. Here are the slides I presented: glaforge.dev/talks/2026/1...

@carnage4life.bsky.social

A feature I really love in #antigravity is the /𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲_𝘂𝗶 slash command which allows me to create some interactive & live widgets in the chat. Like in this example where I display the progress of my running @langchain4j.dev integration tests:

Guillaume Laforge reposted

Astropierre

@astropierre.com

Le saviez-vous? Lorsque, par le passé, l'astrophysicien Hubert Reeves disait que "nous sommes des poussières d'étoiles", il avait parfaitement raison. A part l'hydrogène, tous les autres éléments qui composent votre corps ont été créés lors de différents évènements astrophysiques liés aux étoiles.

Guillaume Laforge reposted

Dare Obasanjo

Google just launched a new website that enables you to verify whether an image, video or audio clip was generated using AI tools that support its SynthID watermark. This includes content from Google, OpenAI, NVIDIA and Kakao, with Apple coming soon.

synthid.comSynthID Detector

Guillaume Laforge reposted

Spock Framework

@spockframework.org

Spock 2.5 is out! 🎉 • Groovy 6.0 support • final variables in where: blocks • Better TooManyInvocationsError diagnostics Heads-up: interactions now stay active in cleanup methods. Release notes: spockframework.org/spock/docs/2... #groovylang

spockframework.orgRelease Notes

There’s a #Devoxx Belgium 2026 speaker list here, if you want to follow the persons who are going to present this year: go.bsky.app/jSCRhV

Guillaume Laforge reposted

Camille Roux

@camilleroux.com

OpenScreen v2.0 est disponible en prerelease. Alternative open source à Screen Studio, gratuite et sans compte. Au menu : montage par la transcription, détourage de la caméra, rendu GPU natif sous Windows, macOS et Linux, serveur MCP pour Claude Code. ⬇️ https://github.com/getopenscreen/openscreen

foojay.ioMy love-hate relationship with Java formattersLearning to love google-java-format, why AI agents make formatters matter even more, and why palantir-java-format now has a fork: open-java-format.

I might give this new #java code formatter a try!

Foojay, the Friends Of OpenJDK@foojay.io

Java formatters: can't live with them, can't live without them. New post on Foojay by Alex Abashev about the tricky balance between automated formatting and personal coding style. foojay.io/today/my-lov... #Java #CodeFormatting #DevLife

Planning your #Devoxx Belgium schedule? With 200+ talks across 8 parallel tracks, picking sessions takes time. I built a personalized agenda generator using #Micronaut, #LangChain4j, and #Gemini 3.5 Flash-Lite on #Java 25 virtual threads! Here is how it works 🧵👇

Instead of one monolithic prompt (30-40s), LangChain4j runs 5 parallel day agents on Java 25 virtual threads via `ParallelMapperAgent`. Run time dropped to ~5s, costing ~1¢. A guardrail agent catches injections early, and deterministic Java code eliminates room collisions.

glaforge.devCrafting a Devoxx Conference Schedule with Gemini, LangChain4j, and MicronautHow I built an AI agent workflow using Gemini 3.5 Flash-Lite, LangChain4j parallel mappers on Java 25 virtual threads, and Micronaut to curate personalized, conflict-free conference schedules for Devo...

Read the full write-up, test the live app, or grab the code: Article: glaforge.dev/posts/2026/0... GitHub: github.com/glaforge/dev... Live app: devoxx-ai-schedule.cloud.run

Is it a 😺 or not? System 1 models like @typesafeai #jev classify, evaluate truthiness, or give a score. I built an app in #java w/ @micronautfw & @langchain4j hosted on #CloudRun to discover if a picture depicts a cat or not, thanks to #DiffusionGemma purrfect-match.cloud.run/

Once you've picked up a picture or uploaded your own, the #DiffusionGemma model running on #NVidia GPUs will tell you if the photo contains a cat, what kind of fur pattern it has, and how fluffy it is:

glaforge.devMultimodal Decision Models: From DiffusionGemma and Jev to LangChain4jHow I adapted Matt Mastracci's djev and Daniel Lee's Cloud Run deployment to run multimodal visual classification on Blackwell GPUs, and proposed multimodal extensions to LangChain4j's StructuredDecisionModel.

For more information and details, I explained how to use Google Gemma's diffusion model with @LangChain4j.dev in #Java here: glaforge.dev/posts/2026/...

Guillaume Laforge reposted

Astropierre

@astropierre.com

Le saviez-vous ? 99,95% de votre masse est contenue dans le noyau des atomes qui composent votre corps. Mais 99% de la masse de ces noyaux est... de l'énergie (les quarks ne comptent que pour 1%). Conclusion, la masse totale de votre corps est à 98,95%... de l'énergie (et 1,05% de particules).

Instead of generating text token by token, "System 1" decision models (like Jev) act as fast, deterministic decision engines. In a single forward pass, they output calibrated probabilities. Here's how I turned DiffusionGemma into a multimodal visual classifier in Java! 🧵👇

Bringing it to #Java with @LangChain4j.dev: LangChain4j was adding StructuredDecisionModel for text. I proposed & implemented native multimodal support. In Java, pass ImageContent with typed Question models (Choice, Noul, Score) for clean, zero-shot visual classification!

github.comtaeold - Overviewtaeold has 80 repositories available. Follow their code on GitHub.

Full story, architecture & code: 👉 glaforge.dev/posts/2026/... Kudos to Matt, & Daniel Lee! Where could you use instant decision models instead of heavy LLMs? Let me know!

The open-source foundation: Matt Mastracci (github.com/mmastrac) built djev on #DeepMind's DiffusionGemma. Using Daniel Lee's recipe (github.com/taeold), I deployed it on Cloud Run with NVIDIA Blackwell GPUs. With min-instances=0, it scales to zero idle (answering in ~140 ms!)

What about images? DiffusionGemma includes a SigLIP vision tower. I turned vision back on in Cloud Run and sent a photo of my cat: 😺 Is it a cat? (99.99%) 👁️ Eye color: Blue (99.99%) ☁️ Fluffiness: Extra fluffy All three questions evaluated concurrently in just 129 ms! 🕑

Text-to-speech has reached a whole new level of quality and personalization. With Google's Gemini 3.8 Flash TTS, you can design custom voices from text prompts, steer delivery nuances (whispers, pacing, emotion), and clone voices. And you can do it all in #Java! 🧵👇

Designing a custom voice in Java takes just a few lines: Voice voice = client.createVoice(Voice.prompted( "A calm, deep French voice, speaking slowly", "French Philosopher", "Gemini 3.8 Flash TTS" )); Pass voice.id() to VoiceConfig. Done.

github.comRelease Release v2.0.2 · glaforge/gemini-interactions-api-sdk🎙️ What's New in v2.0.2 This release introduces comprehensive support for the new Gemini 3.8 Flash TTS models, along with first-class Voice Design, Voice Replication, and conversational turn st...

Walkthrough & code: 👉 glaforge.dev/posts/2026/... Release notes: 👉 github.com/glaforge/ge... What creative voice applications would you build? Let me know!

To hear what this sounds like in practice, watch this demo video: 👉 www.youtube.com/watch?v=FL6... It gives a great taste of how natural the voice quality is, and how prompt-based voice design lets you shape distinct vocal personas with realistic cadence.

youtube.comCreate your own voices with Gemini 3.8 text-to-speechDesign entirely new vocal personas from scratch for gaming, immersi...

I just released v2.0.2 of my Gemini Interactions Java SDK to support these new TTS capabilities: • Voice.prompted(...) for prompt-based voice design • Voice.replicated(...) for voice cloning • Content.speech(text, style) for emotional steering • Direct audio preview access

x.comGoogle Antigravity (@antigravity) on XRun open models like Gemma 4 completely offline in the Antigravity SDK. Built on Google AI Edge’s LiteRT, you can now run Gemma 4 directly on your local GPU. Zero API costs, total data privacy, a…

The #antigravity team announced running local Gemma models on-device with LiteRT. Good news for #Java developers: you can do this in Java too! Antigravity Java SDK v0.2.17 is out, reaching full parity with Python SDK v0.1.18. Walkthrough 🧵👇 glaforge.dev/posts/2026/... x.com/antigravity...

Antigravity Java SDK v0.2.17 also brings: • Subagents with dedicated model targeting (route subtasks to smaller models) • Task scheduling tools (schedule & manage_task) • Tool argument rewriting via hooks • Synchronized native harness across macOS, Linux & Windows

github.comRelease Antigravity SDK for Java v0.2.17 - Local AI Models (LiteRT LM) & Python SDK v0.1.18 Parity · glaforge/antigravity-java-sdkAntigravity SDK for Java v0.2.17 We are thrilled to announce Antigravity SDK for Java v0.2.17! 🚀 This release brings full feature parity with the upstream Python Antigravity SDK v0.1.18 and incorpo...

Full guide & code walkthrough: 👉 glaforge.dev/posts/2026/... Java SDK v0.2.17 on GitHub: 👉 github.com/glaforge/an... What local agent workflows would you build with Antigravity in Java? Let me know!

Step 1: LiteRT-LM setup Install the on-device runtime: pip install litert-lm Download a Gemma model: litert-lm import --model-id litert-community/gemma-4-E2B-it-litert-lm --output-dir ~/.litert-lm/models/gemma4-e2b/ Serve locally: litert-lm serve --port 9379

@olivierleplus.bsky.social

Step 2: Connect from Java Configure your agent with LiteRTAgentConfig pointing to your local model path and port 9379. The SDK manages the harness lifecycle and connects to LiteRT-LM's local endpoint. Call agent.chat() as usual, but completely on-device!

Why run local models for agents? • Zero API costs: run repetitive tasks and test assertions without racking up tokens • Data privacy: proprietary code and docs stay on your machine • Offline capable: build and test without internet • Low latency: no roundtrips over the wire

Guillaume Laforge reposted

Olivier

Not every cool new feature in tech is about AI 😉 I wrote a small article about the "new" CSS feature that FINALLY allows us to customize <select> elements without using JavaScript \o/ builder.aws.com/content/3Jgb...

builder.aws.comCustomizable Select: The <select> dropdown FINALLY catches up with CSS | AWS Builder CenterStyle native dropdowns with CSS, from the picker and checkmark to options with rich HTML. Explore current browser support and three practical examples that keep the browser’s built-in selection behavi...

Guillaume Laforge reposted

Simon Willison

@simonwillison.net

The new Gemini 3.8 TTS models are super-cheap and can generate conversations between multiple voices (from 2,000+, or you can clone your own) - I built a little playground UI for it, then had Claude knock up a script where two pelicans debate moving to Pacifica Pier simonwillison.net/2026/Sep/23/...

Gave a talk at #GDG Cloud Paris about the #antigravity SDK for #Java! While the official SDK is in Python, I built an unofficial Java SDK to bring agent automations to the JVM. Article & 8 code samples 🧵👇 glaforge.dev/talks/2026/...

5️⃣ GitHub PR Review Agent (Main Demo) Combines custom GitHub tools, review rubrics via Agent Skills, subagents, and lifecycle hooks to compare two competing PRs in LangChain4j, stream thoughts live, and produce an objective review report.

github.comGitHub - glaforge/antigravity-java-sdk: An unofficial Java port of the Antigravity AI Agent SDK.An unofficial Java port of the Antigravity AI Agent SDK. - glaforge/antigravity-java-sdk

All 8 samples: 👉 github.com/glaforge/ag... SDK repo: 👉 github.com/glaforge/an... What use cases would you build with Antigravity (Java or Python)? PR review bots in GitHub Actions, CI audits, internal tools? Let me know!

3️⃣ Deny-by-default Security Policies Autonomous agents shouldn't have unrestricted privileges. Configure guardrails with Policies.denyIf(...) to intercept and block destructive operations before execution, allow safe read tools, and fall back to denyAll().

agentskills.ioAgent Skills Overview - Agent SkillsA standardized way to give AI agents new capabilities and expertise.

4️⃣ Open Agent Skills & Session State Load folder-based skills (SKILL.md) for progressive disclosure: keep prompts lean until specialized knowledge is needed. Plus, inject ToolContext into tool methods to store session-scoped state without polluting LLM schemas.

1️⃣ Local Java Tools & Structured Output Annotate Java methods with @Tool and @Param to let the agent call your code. With .finishToolSchema(Record.class), the SDK derives the JSON Schema and deserializes the response directly into your Java record. Zero manual parsing.