# Java Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/java
> Markdown URL: https://aitinkerers.org/technologies/java.md
> Technology record last updated: 2026-02-28T14:41:56Z
> Generated: 2026-09-22T15:50:15Z

Java is the robust, object-oriented programming language designed for platform independence: Write Once, Run Anywhere (WORA).

This is the enterprise workhorse: a high-level, class-based language released in 1995 by Sun Microsystems (now Oracle). Java's core strength is its portability, achieved via the Java Virtual Machine (JVM), which executes compiled bytecode across any supporting operating system. It powers massive, mission-critical systems, cloud applications, and remains foundational to the Android ecosystem. The language is known for its strong memory management, automatic garbage collection, and a vast ecosystem of frameworks like Spring and Jakarta EE, ensuring stability and scalability for complex projects.

- Official technology site: https://dev.java
- Public AI Tinkerers demos and talks: 8
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Somnivox: A Sleep Spell in Your Watch — On-Device AI That Puts You to Sleep](https://montreal.aitinkerers.org/talks/rsvp__xQao8f6FCc)

What if your watch could detect the exact moment your brain is ready to sleep — and play the right sound at the right time to push you over the edge? Somnivox is a Wear OS app that runs a real-time sleep classifier entirely on the watch. No cloud. No phone. No subscription. It monitors your heart rate epoch by epoch, detects when you've been lying awake in bed for 15 minutes, and fades in NSDR audio precisely during the neurological window when it works. The classifier is a personally-calibrated state machine — 5 inputs per epoch, 30 lines of Java, tuned from real overnight data. The next phase replaces it with a quantized LiteRT model trained on multi-tester data, inferring in under 1ms on CPU within the same 17% nightly battery budget. Google shipped LiteRT to production in January 2026 — the timing is perfect. 4 nights of real data. The trigger fired correctly last night. I'll show the epoch replay tool, the raw sensor logs, and the live watch. Looking for Wear OS beta testers and anyone who has shipped a health app on Play Store.

- Event context: AI Tinkerers Montreal - March Demo Night — 2026-03-24 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp__xQao8f6FCc

### [PicoClaw on MaixCam and OpenClaw on Android: Making a Claw Machine](https://manizales.aitinkerers.org/talks/rsvp_ltSlhnfnf4Y)

This is a technical teardown of how I got PicoClaw running on a MaixCam (K210-based) board and OpenClaw on Android client, turning a claw into a live phone hardware controller No slides. Just code, firmware, serial logs, and hardware. The demo will cover: 1. Porting PicoClaw to MaixCam PicoClaw was designed with a specific embedded environment in mind. I’ll walk through: Adapting the firmware to run on MaixCam Fixing build system assumptions Debugging boot and runtime issues We’ll look at: What broke immediately What silently failed What needed to be stubbed or reworked Timing quirks and hardware assumptions in the original firmware This section is mostly about embedded friction and reality. 2. Running OpenClaw on Android On the Android side, we’ll walk through: USB permission handling Threading model Command dispatch UI → Command translation We’ll examine: How commands are built How the app handles connection drops What assumptions the Android client makes about the firmware Where the abstraction leaks This is not a UI demo — it’s a transport-layer autopsy.

- Event context: 🚀 ¡13vo Encuentro de AI Tinkerers Manizales! 🤖 — 2026-02-26 — Manizales
- Public talk page: https://manizales.aitinkerers.org/talks/rsvp_ltSlhnfnf4Y

### [What is an effective AI model for dolphin communication research?](https://montreal.aitinkerers.org/talks/rsvp_ldL1kjb_pss)

I am presenting a working Android app that can be used to embed one or more TFLite models for improved effectiveness. The models need to be developed. Current GenAI models are not a good fit because the data to train them does not exist and their use of image recognition on spectrograms of sounds is not optimal. One tech being considered is the one presented in kyutai.org .

- Event context: AI Tinkerers Montreal: Demo Night — November 20, 2025 — 2025-11-20 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_ldL1kjb_pss

### [AI-Powered Leadership Development: From Talents to Top Leaders](https://prague.aitinkerers.org/talks/rsvp_I0gzZX5LMTY)

I’ll demo the core of the TopLeader platform — an AI-driven system that personalizes leadership and employee development inside organizations. The walkthrough will show how we use large-language-model logic for talent diagnostics, goal-based learning recommendations, and adaptive micro-learning content generation. I’ll open our google cloud project logs and PG Admin to show: - How user data (values, goals, feedback) feeds into the AI personalization engine. - The prompt-engineering layer that produces curated content (articles, learning paths). - How the front-end React components visualize individual and team growth. The demo will run live on our dev environment — no slides, just logs, pg Admin and functionality.

- Event context: 🍂 AI Tinkerers Prague – October 2025 Meetup — 2025-10-23 — Prague
- Public talk page: https://prague.aitinkerers.org/talks/rsvp_I0gzZX5LMTY

### [A platform to embed your model to chat with dolphins at sea](https://montreal.aitinkerers.org/talks/rsvp_Sc0UeVyAbLg)

A working Android application in which a model developer could embed their own TFLite model. Possible functions: 1) filter noise, 2) recognize complex vocalizations, 3) propose acoustic replies.

- Event context: AI Tinkerers Montreal – Spooky October 2025 Meetup — 2025-10-21 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_Sc0UeVyAbLg

### [Generative Business Intelligence](https://nairobi.aitinkerers.org/talks/rsvp_S5kG2rjS44o)

Prompt BI is a revolutionary approach to Business Intelligence, powered by Generative AI, that enables users to interact with data using natural language. Instead of relying on static dashboards or waiting for analysts to run complex queries, users can simply type or speak prompts like “Show me last month’s sales by region” and instantly receive insights, visualizations, or summaries. Behind the scenes, Prompt BI understands the intent through natural language processing, converts it into SQL or equivalent queries, and generates real-time results. It doesn’t just show data—it explains it, recommends actions, and allows users to drill down further through follow-up questions. By automating everything from data integration to insight delivery, Prompt BI democratizes access to data and empowers teams to make faster, smarter decisions without needing technical skills.

- Event context: AI Tinkerers - Nairobi Inaugural Meetup (April) — 2025-04-09 — Nairobi
- Public talk page: https://nairobi.aitinkerers.org/talks/rsvp_S5kG2rjS44o

### [IA powered low code automation tool](https://medellin.aitinkerers.org/talks/rsvp_KbY33Zg1rTM)

SBOT es una herramienta low-code de automatización de pruebas, ahora integrada con IA para acelerar el diseño de casos de prueba, combinando el juicio humano del QA manual con la velocidad de la automatización. Permite crear y ejecutar pruebas de forma fácil desde una interfaz gráfica, integrándose con pipelines CI/CD para optimizar el time to market y la calidad del software.

- Event context: AI Tinkerers Medellín #11 - Science Fair - Agentes en acción — 2025-04-01 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_KbY33Zg1rTM

### [What is the first programming that comes to mind when thinking about machine learning? Java, obviously!](https://dubai.aitinkerers.org/talks/rsvp_FvrdF9y3kE0)

I am participating in a kind of hackaton, and I am trying to build a RAG system that can extract relevant information from the du website. Because I love Java, Spring and Neo4J I decided to make my life easier by using Java and Spring instead of Python and Neo4J for vector embeddings instead of stuff like quarkus. The experience so far has been bumpy but I learned a lot about the internal workings of the Neo4J vector storage and I enjoyed how much boilerplate I did *not* have to write compared with Python. I will demo where am with the project: at the moment I successfully crawled the du website and stored the documents in the neo4j vector store. I am trying to use llama 3.1 to automatically come up for tags for the webpages, so that I can then pre-filter the pages by tag instead of just using cosine similarity, which has been quite poor so far I expect to show: * how to setup Spring AI to create embeddings using ollama and llama 3.1 * how to setup neo4j so that it can be used as a vector store * how to setup a chat model so that you can "talk" to llama 3.1 The main takeaway from this is how little code I had to write to make all this work, leveraging Spring autoconfiguration, and how cosine similarity can be not as good as expected with real world data

- Event context: AI Tinkerers - Dubai Meetup #2 (October) — 2024-10-05 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_FvrdF9y3kE0

## Related Technologies

- [Android](https://aitinkerers.org/technologies/android) ([Markdown](https://aitinkerers.org/technologies/android.md)) — 11 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Android 11](https://aitinkerers.org/technologies/android-11) ([Markdown](https://aitinkerers.org/technologies/android-11.md)) — 1 public demo
- [C](https://aitinkerers.org/technologies/c-2) ([Markdown](https://aitinkerers.org/technologies/c-2.md)) — 6 public demos
- [C++](https://aitinkerers.org/technologies/c) ([Markdown](https://aitinkerers.org/technologies/c.md)) — 10 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [Edge processing](https://aitinkerers.org/technologies/edge-processing) ([Markdown](https://aitinkerers.org/technologies/edge-processing.md)) — 1 public demo
- [ExoPlayer](https://aitinkerers.org/technologies/exoplayer) ([Markdown](https://aitinkerers.org/technologies/exoplayer.md)) — 1 public demo
- [Google Cloud Platform](https://aitinkerers.org/technologies/google-cloud-platform) ([Markdown](https://aitinkerers.org/technologies/google-cloud-platform.md)) — 25 public demos
- [Google Pixel](https://aitinkerers.org/technologies/google-pixel) ([Markdown](https://aitinkerers.org/technologies/google-pixel.md)) — 1 public demo
- [Hydrophones](https://aitinkerers.org/technologies/hydrophones) ([Markdown](https://aitinkerers.org/technologies/hydrophones.md)) — 1 public demo
- [K210](https://aitinkerers.org/technologies/k210) ([Markdown](https://aitinkerers.org/technologies/k210.md)) — 1 public demo
- [Kotlin](https://aitinkerers.org/technologies/kotlin) ([Markdown](https://aitinkerers.org/technologies/kotlin.md)) — 6 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [LiteRT](https://aitinkerers.org/technologies/litert) ([Markdown](https://aitinkerers.org/technologies/litert.md)) — 2 public demos
- [Llama 3](https://aitinkerers.org/technologies/llama-3) ([Markdown](https://aitinkerers.org/technologies/llama-3.md)) — 38 public demos
- [MaixCam](https://aitinkerers.org/technologies/maixcam) ([Markdown](https://aitinkerers.org/technologies/maixcam.md)) — 1 public demo
- [MongoDB](https://aitinkerers.org/technologies/mongodb) ([Markdown](https://aitinkerers.org/technologies/mongodb.md)) — 15 public demos