# JavaScript Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/javascript
> Markdown URL: https://aitinkerers.org/technologies/javascript.md
> Technology record last updated: 2026-09-18T15:13:38Z
> Generated: 2026-09-21T16:50:36Z

A zero-dependency architecture using native browser APIs to deliver sub-100ms load times on static hosting.

This approach replaces heavy frameworks with native DOM manipulation and ES6+ modules. By deploying to global CDNs like Vercel or Netlify, you bypass server-side processing and reduce total bundle sizes by over 90%. It is the optimal choice for high-traffic landing pages or internal tools where speed, security, and long-term maintainability are the primary requirements.

- Official technology site: https://developer.mozilla.org/en-US/docs/Web/JavaScript
- Public AI Tinkerers demos and talks: 40
- Result page: 1 of 2

## Recent Public Talks and Demos

### [Orquestração multi-agente em n8n: sub-workflows virando tools dinâmicas](https://curitiba.aitinkerers.org/talks/rsvp_F61Msr-AenQ)

Construí um sistema multi-agente que opera o assistente de WhatsApp de uma marca brasileira de suplementos "clean label" com catálogo de 20+ SKUs em 8 categorias (sono, estética, emagrecimento, imunidade, saúde feminina 40+, entre outros) e dois canais ativos de WhatsApp para quiosque físico e delivery. O problema real: volume de perguntas simultâneas sobre produtos específicos (composição, indicação, contraindicação, disponibilidade), mix de intenções radicalmente diferentes: consumidora final comprando pela primeira vez, cliente em recompra, nutricionista prescrevendo e a necessidade de escalar atendimento sem perder o tom consultivo que a marca construiu. Em vez de LangGraph ou CrewAI, usei n8n como orquestrador e Claude como motor de decisão. Mensagens chegam via Evolution API num webhook do n8n; o Claude classifica a intenção (tool use) e roteia para a tool certa; mas cada "tool" é um sub-workflow n8n separado, chamado via Execute Workflow. Cada sub-workflow tem seu próprio prompt, seu próprio acesso ao Supabase (RAG sobre o catálogo completo com pgvector, histórico de pedidos, perfil do cliente) e seu próprio guard-rail. Quando a confiança do Claude cai especialmente em perguntas clínicas sobre contraindicações, o agente passa para humano via Chatwoot. Tudo self-hosted na Hetzner (Docker Swarm + Traefik). Na demo ao vivo mostro: uma mensagem real chegando no WhatsApp, o painel do n8n executando nó a nó, o sub-workflow correto ativando como tool, e os logs no Supabase. Compartilho o padrão "sub-workflow-as-tool" e o JSON exportado.

- Event context: AI Tinkerers Curitiba: Evento Inaugural — 2026-06-10 — Curitiba
- Public talk page: https://curitiba.aitinkerers.org/talks/rsvp_F61Msr-AenQ

### [Building My Own Piano Teacher Because I'm Too Impatient for YouTube](https://nurnberg.aitinkerers.org/talks/rsvp_NveTwvTUV4E)

I totally vibe coded a browser-based piano learning app that uses your microphone to detect pitches and gamifies music theory with timed challenges. (I've never really seen the code.) Demo: 1. Show the app and what it can do 2. Show my workflow: Prompting in Claude Code to add another feature 3. Showing the infrastructure (hosting for free with static website on Github Pages, using localStorage as Database)

- Event context: AI Tinkerers Nürnberg: April Meetup — 2026-04-22 — Nürnberg
- Public talk page: https://nurnberg.aitinkerers.org/talks/rsvp_NveTwvTUV4E

### [Moonshine: distilling interactive technical explanations](https://atlanta.aitinkerers.org/talks/rsvp_VaMWMEBQbr4)

https://github.com/enjalot/moonshine moonshine is a skill for distilling interactive technical explanations from AI generated complexity. I'll show some examples of articles I've built, including documentation for my open source projects which have gotten more complex with new AI assisted additions.

- Event context: AI Tinkerers Atlanta: Community Demos & Technical Deep Dives — 2026-04-21 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_VaMWMEBQbr4

### [How AI Agents Work, from while to wow!](https://paris.aitinkerers.org/talks/rsvp_cVHew7whhkA)

A clone of OpenCLAW to learn how it works

- Event context: AI Builders Meetup Paris - OpenClaw (featuring 42 AI & HEC Vibe) — 2026-03-26 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_cVHew7whhkA

### [GitOps for Rules: Tests, Signatures, and Policy Diffs for Changing Requirements](https://bremen.aitinkerers.org/talks/rsvp_JWF02w4zz2M)

I will demo a workflow that treats “rules” like deployable software artifacts. Starting from a policy module in YAML, I will show how changes produce a readable diff, trigger golden tests, generate a cryptographic signature, and publish a versioned module. Then I will run a batch simulation to quantify what the change actually does (block/flag rates, which rules fired, what shifted). Finally, I will export an evidence bundle for a single decision containing the module hash + trace. Code walkthrough only: diffing, test harness, signing, and the simulation runner.

- Event context: AI Tinkerers Bremen — 2026-03-25 — Bremen
- Public talk page: https://bremen.aitinkerers.org/talks/rsvp_JWF02w4zz2M

### [Domain-encoded system prompts: turning 15 years of accounting forensics into a live Claude diagnostic tool](https://montreal.aitinkerers.org/talks/rsvp_x6xfCYXZsaM)

I built a structured diagnostic engine that ingests raw ADP Workforce Now payroll exports and NetSuite GL data, routes them through a domain-encoded Claude system prompt, and returns a JSON-structured root cause analysis — including the specific fix — for recurring payroll-GL discrepancies that human reviewers consistently miss. The demo runs live against the Anthropic Messages API. The input is a real payroll pattern: employer burden accounts (CPP, EI, CNESST, RQAP) posting at exactly 0.500x expected in every quarter-end month for three years. The system prompt carries the diagnostic heuristics — check ratio before amount, look for N-period calendar patterns, separate gross wages from employer burden — that normally live inside a practitioner's head. Claude doesn't discover these rules. They're injected. The output is a structured JSON object with root_cause, confidence_pct, adp_fix_steps[], correcting_je_description, and cfo_memo.

- Event context: AI Tinkerers Montreal - March Demo Night — 2026-03-24 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_x6xfCYXZsaM

### [Writing our own JavaScript for "Code Mode" MCP](https://nyc.aitinkerers.org/talks/rsvp__yv2FaDF35s)

How we built two javascript runtimes in Rust using the "Deno" crate. - How we embedded typescript instant type checking of LLM generated code - How we embedded a Rust MCP client - How we lean on Deno configurations for sandboxing rules

- Event context: March Demo Day, hosted by Flowglad — 2026-03-18 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp__yv2FaDF35s

### [Claude does queuing](https://manchester-nh.aitinkerers.org/talks/rsvp_d1ggwXXOkoE)

I asked Claude to generate a simulation of a simple deterministic queueing system in JavaScript, and to output the results as a set of three graphs using Plotly. I wrote moderate length prompt with very clear specifications for the model of the system and the desired output. I validated the results using an identical model that I created manually in the MathWorks SimEvents product. My goal was primarily experimentation, my own personal learning, and the evaluation of Claude's capabilities.

- Event context: AI Tinkerers Manchester (Bedford), NH - March 2026 Meetup — 2026-03-18 — Manchester NH
- Public talk page: https://manchester-nh.aitinkerers.org/talks/rsvp_d1ggwXXOkoE

### [OpenClaw-Powered Port: Turning a Figma Plugin into a Standalone Web App with Claude + Grok](https://tokyo.aitinkerers.org/talks/rsvp_WdjiLvvXPiU)

I'll demo how I migrated Humation — a hand-drawn avatar system used by 60k+ people — from Figma Plugin to standalone web app using ONLY AI agents via OpenClaw (Claude Opus + Grok). No manual coding: I'll live-show the prompts, iterative generations, debugging hacks, SVG handling quirks, performance fixes, and unexpected failures/successes that made it work. Core logic remains simple part-layering, but AI handled the entire porting chaos.

- Event context: AI Tinkerers Tokyo - Toranomon Meetup - February 19, 2026 — 2026-02-19 — Tokyo
- Public talk page: https://tokyo.aitinkerers.org/talks/rsvp_WdjiLvvXPiU

### [Railtracks](https://toronto.aitinkerers.org/talks/rsvp_QYJgtAs5WJo)

The first Canadian agentic framework, fully free and open-source, was developed by the software community at UBC, UofT and Amii. It has a great quality as all contributors and advisors (no-code) are from big AI firms in Canada. The license is MIT The project is at an early stage (<2 months) and fully usable, while a bit larger in scale, it is quite early and matches greatly with the Tkinter theme. A video is in preparation, but will require at least a week (jan 20) to be ready

- Event context: AI Tinkerers Toronto - January 2026 Meetup at Google! — 2026-01-29 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_QYJgtAs5WJo

### [Why I dropped using REST for MCPs and started using GraphQL.](https://poland.aitinkerers.org/talks/rsvp_ZT1zz0ewZj8)

GraphQL offers huge benefits over REST for querying relational data. Yet almost no examples online use it. i'll present how huge impact on quality of tool calling, reducing the network load & tokens usage GraphQL has when implemented as MCPs. I'll cover: - when should MCP use GraphQL - how to implement MCP with GraphQL-like interface - how to use MCPs that use GraphQL-like interface - real-life impact on development speed, infrastructure, llm costs.

- Event context: AI Tinkerers Poland #6 - Meetup in Warsaw (26th November) — 2025-11-26 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_ZT1zz0ewZj8

### [AI-Powered Lead-to-Conversion Automations Using n8n + LLMs](https://tiruchirappalli.aitinkerers.org/talks/rsvp_7jf5H6xXPrY)

This session showcases how businesses can automate their entire lead management cycle using n8n and Large Language Models (LLMs). From collecting incoming leads to generating summaries, follow-up reminders, WhatsApp updates, and smart insights, you’ll learn how AI can convert raw lead data into actionable decisions — automatically. Perfect for founders, digital marketers, and creative teams who want to reduce manual work and boost conversions using no-code intelligence.

- Event context: AI Tinkerers Tiruchirappalli Meetup — Demo Proposals Open — 2025-11-22 — Tiruchirappalli
- Public talk page: https://tiruchirappalli.aitinkerers.org/talks/rsvp_7jf5H6xXPrY

### [DocStream: An Educational AI Agent](https://toronto.aitinkerers.org/talks/rsvp_xZuNIhPO2xA)

The objective of DocStream is to automate developer documentation by transforming raw terminal activity into structured, reusable artifacts. Rather than merely generating code, DocStream focuses on helping users detect and recover from errors, providing contextual guidance on what has been done, what is currently happening, and what remains to be completed. This demo showcases the current development progress of the DocStream tool. The system is designed as a multi-model pipeline, though the current implementation includes only Model 0 and Model 1. Event data is streamed through Model 0 (for parsing and annotating into different event groups) and Model 1 (for summarization and explanation of the parsed events). Together, these components help users, especially newcomers to understand what each terminal command does and why it matters.

- Event context: AI Tinkerers Toronto - November 2025 Meetup at Shopify! — 2025-11-10 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_xZuNIhPO2xA

### [De la pereza a la automatización](https://manizales.aitinkerers.org/talks/rsvp_rEVE7dOTXik)

En esta charla voy a contar mi experiencia a lo largo de los años con diferentes formas de automatizar, proyectos y tareas del día a día

- Event context: 🏔️ ¡Noveno Encuentro de AI Tinkerers Manizales! — 2025-10-29 — Manizales
- Public talk page: https://manizales.aitinkerers.org/talks/rsvp_rEVE7dOTXik

### [Orquestación y especialización de agentes código](https://medellin.aitinkerers.org/talks/rsvp_53m46l-k0-k)

Un camino en como de manera personal orquestro reviso y especializo agentes para ser 10x developer.

- Event context: AI Tinkerers Medellín #16 - Lean Solutions Group - 25 de Septiembre — 2025-09-26 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_53m46l-k0-k

### [AI automation Agents](https://nairobi.aitinkerers.org/talks/rsvp_msMfL7yMAEs)

I have 4 AI agent to present, 1. Website Chatbot agent that can be embedded on any website to automate support and enquiry (customizable widget) 2. Voice agent powered by elevenlabs backend orchestrated by n8n 3. Email classifier agent and auto responder 4. WhatsApp Chatbot

- Event context: AI Tinkerers Nairobi – Sep 25, 2025 Meetup — 2025-09-25 — Nairobi
- Public talk page: https://nairobi.aitinkerers.org/talks/rsvp_msMfL7yMAEs

### [Workflow con stack tecnológico, usando n8n, evolution api e Easy Panel con integración en redes sociales (Facebook, WhatsApp)](https://pereira.aitinkerers.org/talks/rsvp_w8IcmRfAOu4)

Quiero compartir un proyecto que esta actualmente en producción con enfoque en automatización de procesos en redes sociales con grandes volúmenes de actividad, en esta solucion se integra un stack tecnologico a traves de la plataforma de EasyPanel, en la cual se administra n8n, base de datos (PostgreSQL), habilitando el uso de whatsapp con evolution api, integracion de agentes de open AI, y codificación en lenguajes como Javascript, usando estrategias inteligentes de Engineer Prompting.

- Event context: AI Tinkerers Pereira: De Usuarios a Makers: Prototipos que Inspiran — 2025-09-24 — Pereira
- Public talk page: https://pereira.aitinkerers.org/talks/rsvp_w8IcmRfAOu4

### [A Mindless Dialogue: What if two LLMs start debating with eachother about random stuff.](https://hamburg.aitinkerers.org/talks/rsvp_Ip6qa79jbxw)

In this presentation, I will show what happens when two LLMs start descussin various topic with each other. The focus will be on showing my learnings about the memory functions of Large Language Models (LLMs). I will show the underlying code and techniques like offline live text-to-speech functionality. To showcase the conversational abilities of AI through various use cases, including discussing different topics with each other. To provide a detailed explanation of the memory functions present within Large Language Models (LLMs). To demonstrate the coding techniques used to implement memory in LLMs. To introduce live text-to-speech functionality and allow participants to experience AI-generated speech.

- Event context: AI Tinkerers Hamburg #3 - August 14 — 2025-08-14 — Hamburg
- Public talk page: https://hamburg.aitinkerers.org/talks/rsvp_Ip6qa79jbxw

### [Desafío Vibe Coding de Broky; Pasar de prototipo a producción](https://santiago.aitinkerers.org/talks/rsvp_Ze6hFgRP2_Y)

El objetivo de nuestra presentación es mostrar el sistema agéntico de Broky desarrollado en N8N. Lo que se busca es recibir feedback y consejos para pasar toda esa estructura a código y que sea mucho más escalable de la mejor y más optima forma posible.

- Event context: 🔥 AI TINKERERS – SANTIAGO / CAPÍTULO 6 — 2025-07-31 — Santiago
- Public talk page: https://santiago.aitinkerers.org/talks/rsvp_Ze6hFgRP2_Y

### [Can You Trust the AI?](https://dc.aitinkerers.org/talks/rsvp_de5ZCyZkik8)

How do we use large language models (LLMs) safely? How do we check the AI response? We are working on an app builder service with AI assitanet and we use these methods to validate the AI response: - JSON schema - JavaScript expression validation - Solution Graph and diagram for user validation - Other AI instance to fix errors by LLM

- Event context: AI Tinkerers - DC Metro Meetup (July 10th 2025) — 2025-07-10 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_de5ZCyZkik8

### [Sovereign Voice AI for Indic languages that listens, learns and perform agentic searches.](https://delhi.aitinkerers.org/talks/rsvp_zSlwbXmB6ms)

I will be presenting a demo on how to build a Sovereign voice-first AI interface built for the rich diversity of Indic languages. The demo will be capturing spoken input, understanding and retaining -provided facts, perform context-aware agentic searches and taking actions on user's behalf. All built on open-source, sovereign infrastructure to keep data within national borders yet leveraging widely available ecosystem tools.

- Event context: AI Tinkerers - Delhi - June Meetup — 2025-06-28 — Delhi
- Public talk page: https://delhi.aitinkerers.org/talks/rsvp_zSlwbXmB6ms

### [Browser Operator: Web Browser with AI Agents](https://seattle.aitinkerers.org/talks/rsvp_iJiZYeLL_rA)

Will be walking through my implementation of multi-agent framework to support building AI agents on the browser. Showcase some of the architecture decisions and pitfalls I faced while building the browser platform. Also, show how its important to support privacy friendly local first AI browser which has access to sensitive data. https://browseroperator.io/

- Event context: AI Tinkerers Seattle – June Meetup — 2025-06-28 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_iJiZYeLL_rA

### [Instant AI: Train an Image Classifier in Your Browser (No PhD Required!)](https://amsterdam.aitinkerers.org/talks/rsvp_weAS-wPOMfA)

Ever wished you could teach your computer to tell the difference between your cat and your lunch (who hasn't?) - without a supercomputer and a PhD? I'll show you how to build a custom image classifier right in your browser using TensorFlow.js. We’ll use the magic of transfer learning (and a little help from MobileNet) to create a surprisingly smart model with just a handful of your own photos. No servers, no installs, no tears - just you and your browser.

- Event context: AI Tinkerers x AdvancedJS Amsterdam — 2025-06-25 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_weAS-wPOMfA

### [Creating AI Agents in JavaScript](https://miami.aitinkerers.org/talks/rsvp_m6id4m01LSs)

I’ll demo how I built a multi-agent system in pure JavaScript, where agents collaborate to complete complex tasks using LLMs, tool usage, and a shared memory model. The system is entirely open source, built using KaibanJS, and runs both in Node.js and the browser. I’ll walk through: - How agents are defined using roles and goals - How they plan, act, and react with real-time state updates - The architecture behind teams, tools, and LLM integrations - A live coding walkthrough showing agents solving a real problem together No slides. Just code and agents at work.

- Event context: AI Tinkerers - Miami: May Meetup at The LAB — 2025-05-29 — Miami
- Public talk page: https://miami.aitinkerers.org/talks/rsvp_m6id4m01LSs

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [n8n](https://aitinkerers.org/technologies/n8n) ([Markdown](https://aitinkerers.org/technologies/n8n.md)) — 45 public demos
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 99 public demos
- [HTML](https://aitinkerers.org/technologies/html) ([Markdown](https://aitinkerers.org/technologies/html.md)) — 9 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [CSS](https://aitinkerers.org/technologies/css) ([Markdown](https://aitinkerers.org/technologies/css.md)) — 6 public demos
- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos
- [Supabase](https://aitinkerers.org/technologies/supabase) ([Markdown](https://aitinkerers.org/technologies/supabase.md)) — 90 public demos
- [bash](https://aitinkerers.org/technologies/bash) ([Markdown](https://aitinkerers.org/technologies/bash.md)) — 12 public demos
- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [Flask](https://aitinkerers.org/technologies/flask) ([Markdown](https://aitinkerers.org/technologies/flask.md)) — 24 public demos
- [GitHub](https://aitinkerers.org/technologies/github) ([Markdown](https://aitinkerers.org/technologies/github.md)) — 74 public demos
- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos

## More Results

- Next: https://aitinkerers.org/technologies/javascript.md?page=2