# Cloudflare Workers Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/cloudflare-workers
> Markdown URL: https://aitinkerers.org/technologies/cloudflare-workers.md
> Technology record last updated: 2026-09-18T15:13:46Z
> Generated: 2026-09-20T18:47:38Z

Deploy serverless code instantly on Cloudflare's global network, executing with zero cold starts via V8 isolates for ultra-low latency.

Cloudflare Workers is your serverless compute platform: run JavaScript, TypeScript, or WebAssembly directly on Cloudflare's global edge network. Leveraging the V8 engine and its isolate architecture ensures near-instant startup (zero cold starts), delivering ultra-low latency to users in over 330 cities. Use Workers to deploy fast edge logic—from custom API gateways and request routing to modifying responses and running AI inference—without managing a single server.

- Official technology site: https://developers.cloudflare.com/workers/
- Public AI Tinkerers demos and talks: 22
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Company of zero on CloudFlare workers - discord and web - SharePoint and GitHub](https://columbus.aitinkerers.org/talks/rsvp___929LQGfqg)

AnimaMesh operates a company-of-0: an organization whose entire back office — compliance calendar, bookkeeping, document librarianship, board governance, research watch, inbound triage — is run by a mesh of AI agents. One human (the principal) supplies judgment and signatures. Everything else wakes up on its own heartbeat, reads the company's knowledge, does the preparable work, and reports back: "here's what I found, here's the draft, approve or edit."

- Event context: AI Tinkerers - Columbus August Meetup — 2026-08-03 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp___929LQGfqg

### [Orchestrating attention with human-on-the-loop](https://seattle.aitinkerers.org/talks/rsvp_yjRZexQA3q8)

I built a new notification paradigm in https://comment.io, the Multiplayer Markdown Editor, that helps orchestrate not just agents but the people who work with them

- Event context: AI Dev Tools Track - Seattle - July 13 — 2026-07-14 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_yjRZexQA3q8

### [Coding is Solved. Next Up: Figure Out How to Plan](https://seattle.aitinkerers.org/talks/rsvp_-1Uv6ETOTq8)

I built an Agent-Native Google Docs to review, edit, and share plans in Markdown

- Event context: AI Dev Tools Track - Seattle — 2026-05-06 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_-1Uv6ETOTq8

### [Jules: An AI Agent That Thinks, Argues, and Writes](https://austin.aitinkerers.org/talks/rsvp_f0lg_KSKY8s)

I built Jules — a Claude Code-based AI agent with a personality, opinions, and structured decision-making workflows. Jules isn't just a coding assistant — it's a strategic thinking partner that follows multi-step reasoning processes, pushes back on my ideas, runs adversarial reviews before recommending anything, and writes content in my voice. I'll demo the live system: how a single prompt triggers structured thinking workflows with visible reasoning steps, how the agent challenges my framing before agreeing with me, and where this is headed — multi-agent coordination through Paperclip and a conversational gateway called Hermes.

- Event context: AI Tinkerers Austin: April 2026 Demo Night — 2026-04-16 — Austin
- Public talk page: https://austin.aitinkerers.org/talks/rsvp_f0lg_KSKY8s

### [Killing Guesswork in Outbound: A Multi-Agent Sales Engine That Thinks Before It Writes](https://houston.aitinkerers.org/talks/rsvp_5E60bBy5MV8)

I built a multi-agent sales engine that researches a prospect before any outreach happens, using a pipeline of specialized AI agents to generate structured intelligence, map relationships, and produce context-aware messaging. Instead of writing cold emails directly, the system runs 7 agents in sequence (identity, profile, activity, market, network, scoring, synthesis) to turn raw internet data into a decision-ready sales brief and outreach strategy. The demo shows how a single name + company turns into: structured research inferred network graph signal-based scoring generated outreach grounded in actual context

- Event context: AI Tinkerers Houston: April Meetup — 2026-04-14 — Houston
- Public talk page: https://houston.aitinkerers.org/talks/rsvp_5E60bBy5MV8

### [Building an end-to-end agentic coding workflow in sandbox](https://seattle.aitinkerers.org/talks/rsvp_A0CI_bsvMlY)

I’ll do a live technical walkthrough of an AI-assisted developer workflow that turns a task into code changes, tests, and a PR-ready diff. I’ll show the actual implementation: task orchestration, sandboxed execution, tool-calling, retry/failure handling, and human-in-the-loop checkpoints. This is a code-only demo (no slides), including what broke, what was hacked together, and what made the workflow reliable enough for daily use.

- Event context: AI Dev Tool Track — Seattle Meetup - April 13th, 2026 — 2026-04-14 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_A0CI_bsvMlY

### [SaveSora: Downloading & Watermark Removal for OpenAI Sora Videos](https://dc.aitinkerers.org/talks/rsvp_zio-5LxaGn4)

SaveSora is a free web tool that breaks through OpenAI Sora's download restriction. Sora only lets you download your own videos — SaveSora lets you grab any publicly shared Sora video via link, view its original generation prompt, and remove the Sora 2 watermark automatically. No login, no fees, works in the browser instantly.

- Event context: AI Tinkerers x Softengi - DC Metro Meetup - April 9th, 2026 — 2026-04-09 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_zio-5LxaGn4

### [Gist - Read More. Think Deeper. Learn Faster.](https://orange-county.aitinkerers.org/talks/rsvp_h9HyI5ORZ1U)

**If you are suffering from information overload, Gist is for you.** Gist is a browser extension that distills research papers, YouTube videos, and webpages into structured understanding — without opening a new tab. Hit the button and an overlay appears on top of the page you're already reading. If you have 47 unread Arxiv.org tabs open right now — Gist is for you. If your appetite for learning exceeds your time budget — Gist is for you. --- Most AI summarizers give you slop. Gist structures content the way a PhD would — differently depending on what the content actually is. **Arguments → Logical structure:** Thesis, evidence, counter-argument, synthesis. Built for research papers and analytical content. **Stories → Dramatic structure:** Situation, complication, question, resolution. The shape every good story already has. --- **Gist goes beyond summarization** when it detects an argument: **Counter-argument:** The strongest possible case against the author's position — not a disclaimer, the actual objection. **Steelman:** An even stronger version of the author's argument, rebuilt from scratch. You don't just learn what the author thinks. You learn exactly where they might be wrong. Gist makes the: - Complex → Comprehensible - Boring → Interesting - Slow → Fast It’s a graduate school seminar in your browser, on-demand. ⸻ **One click. Layered understanding.** - First slide: One sentence — the irreducible core of the entire piece - Swipe: Context, complications, evidence, counter-arguments - Stop anytime: You control the depth - No new tabs: Gist overlays the page you’re reading The original is always there. Gist is a pre-read — helping you decide whether to invest the time, and priming your mind to comprehend it if you do. ⸻ **Share the Gist** Share the Gist of anything as a link. - Recipient doesn’t need Gist installed - Recipient doesn’t need to sign up - They click, they see the same Gist you saw (with a link to the original) Share the Gist of a 40-page arXiv PDF in a Slack message. Send the Gist of a 2-hour YouTube podcast over WhatsApp. Gist is your Instagram filter for the internet.

- Event context: AI Tinkerers OC - March 11, 2026 Meetup — 2026-03-12 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_h9HyI5ORZ1U

### [AI Workers That Create and Operate Their Own MCP Apps](https://berlin.aitinkerers.org/talks/rsvp_sC1XxmRx7x8)

A platform where AI workers (tedis) autonomously build, deploy, and operate MCP apps, both internal tools and customer-facing products as ChatGPT apps. Not "AI-assisted development." The Tedi IS the developer, the ops engineer, and the product manager. I'll walk through the technical build: - The MCP app lifecycle: A tedi takes an API endpoint, maps it to MCP tools (config-driven D1 rows, zero handler files), generates widget layouts via genUI, validates output with screenshot-based QA (Cloudflare Browser Rendering → R2), and deploys — all autonomously. - 131 tools, one universal handler: Every MCP tool is a database row. Adding a tool = inserting a row. No code, no deploy. - Persistent memory for improvement: Tedis carry a semantic knowledge graph (Brain MCP: Upstash Vector + D1) so each app they build is better than the last. Patterns, gotchas, and architecture decisions compound across sessions.

- Event context: AI Tinkerers Berlin Meetup - March 11, 2026 — 2026-03-11 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_sC1XxmRx7x8

### [Edge-First AI: Per-Student Agents on Cloudflare](https://singapore.aitinkerers.org/talks/rsvp_2uQx8tjb9FA)

ow we built mcq.sg - an AI tutoring platform where every student gets their own stateful agent. The defining infrastructure choice: Cloudflare Durable Objects. Each student has a dedicated DO with built-in SQLite storing mastery data, attempt history, and recommendation queue. The AI agent runs inside the DO - no centralized database, no bottleneck, no cold starts for returning students. I'll show the code for: - Per-student DO with local SQLite schema - Multi-model extraction pipeline (Moondream for detection, Claude for reasoning) - Async batch processing for 50% cost savings on non-realtime tasks Built by 2 people. Previously led engineering on ParkingSG and RedeemSG at Open Government Products.

- Event context: AI Tinkerers - The Age of AI & Infrastructure (Singapore) — 2026-02-11 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_2uQx8tjb9FA

### [Vibe Presenting -> Recreating Cursor-like flow for creating high-quality presentaitons](https://poland.aitinkerers.org/talks/rsvp_saFLZPAgflQ)

When I was creating business presentations, I often felt frustrated that I could develop things very quickly using vibe coding, but producing a truly high-quality presentation was still a very manual process. While apps like Gamma exist, they’re mostly designed around generating *at most* decent presentations in seconds. For me, the goal isn’t necessarily to minimize the time spent creating presentations, but rather to maximize their quality within a given time budget. So I started vibe coding presentations as simple frontend apps with layour like presentation. I've also spotted other people on my team doing the same. It's cool to do manually, but there is some config, setup, dumping etc. problems. So I started coding app which does it for you. And now it seems pretty useful :D

- Event context: AI Tinkerers Poland & GDG #2 - Meetup in Wrocław — 2026-01-27 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_saFLZPAgflQ

### [Building a Real-time Voice Agent with Cloudflare's Edge Stack](https://montreal.aitinkerers.org/talks/rsvp_FZMBRFtgd6Q)

Live demo of a sales pitch coaching app built entirely on Cloudflare: Durable Objects for stateful WebSocket sessions, Workers AI for real-time transcription and LLM inference, Vectorize for RAG, and R2 for document storage. I'll walk through the architecture decisions, show how structured extraction beats naive RAG chunking, and demo the app coaching a live pitch with realtime insights and post-session scoring.

- Event context: AI Tinkerers Montreal - January 2026 Meetup at Ateko — 2026-01-21 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_FZMBRFtgd6Q

### [Why Context Management Matters](https://poland.aitinkerers.org/talks/rsvp_osx2ngU7ESU)

I'll be talking about one of the most important skills of today - context management. It's single handedly the biggest thing that separates getting results with AI from vibe coded slop. Also would love to talk about Conare - the app I build to solve the problem. This is my first AITinkerers, so if it goes against the spirit - no problem. But it really solves this problem nicely!

- Event context: AI Tinkerers Poland #6 - Meetup in Warsaw (26th November) — 2025-11-26 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_osx2ngU7ESU

### [Challenges and Solutions to building a Natural Voice-based Survey Agent](https://dhaka.aitinkerers.org/talks/rsvp_6rUaxSv5qaM)

I'll be showing an in-progress build for a prototype voice survey agent that a user can use both as a research assistant to help them brainstorm and craft out what they'd like to find out from the interview, and can also function as a interviewer, utilising a discussion guide to make sure everything that needs to be asked is asked, as well as asking probing questions to respondents if they respond vaguely.

- Event context: AI Tinkerers Dhaka Inaugural Meetup - Dhaka Builds with AI — 2025-11-01 — Dhaka
- Public talk page: https://dhaka.aitinkerers.org/talks/rsvp_6rUaxSv5qaM

### [Agents as Apps](https://waterloo.aitinkerers.org/talks/rsvp_S2DowknGHSI)

How can we share agents as easily as we can install phone apps from the app store? In addition to the usual trust and safety elements (like a clear permissions model with enforced boundaries), there's also the challenge of limiting token usage in a way that balances predictable costs with user experience. I'll demo something I'm playing with using Cloudflare's Dynamic Workers Loader, which offers a bit of a sweet spot in terms of sandboxing and capabilities. We'll look at how to safely execute arbitrary code, measure the resources consumed, and enforce flexible limits by supporting agents going into a capped amount of debt.

- Event context: AI Tinkerers Waterloo — October Meetup — 2025-10-20 — Waterloo
- Public talk page: https://waterloo.aitinkerers.org/talks/rsvp_S2DowknGHSI

### [Claude Draws (/ how to automate Claude for Chrome)](https://sf.aitinkerers.org/talks/rsvp_zvyMJwwAAEI)

Claude Draws is an interactive community art project which challenges Claude to bring your idea to life using the hottest graphic design software from 1989, Kid Pix. I'll give a live demo of Claude Draws, built on top of the Claude for Chrome research preview. I'll also talk about how I built Claude Draws, some best practices for building browser agents, and a few lessons I learned along the way.

- Event context: Agents in Production: Human in the Loop Orchestration w/ Temporal — 2025-10-17 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_zvyMJwwAAEI

### [Speedrun building a monetized (remote) MCP server](https://london.aitinkerers.org/talks/rsvp_YLebPiED5ug)

Remote MCP servers have the potential to be the app-store moment for LLMs, picking up where "custom GPTs" failed. So what does any tinkerer do? Build and ship! I'd like to present how to go from 0 to $ in a weekend using Cloudflare workers, Supabase, and Stripe The example I'll walkthrough allows an LLM client to make phone calls on the users behalf - Dialer

- Event context: AI Tinkerers London Meetup - July 16th, 2025 — 2025-07-16 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_YLebPiED5ug

### [Real-Time AI Infrastructure for the Multi-Agent Era: Building AG-UI Protocol in Pure Rust](https://la.aitinkerers.org/talks/rsvp_gG7geaVHf64)

I'll demonstrate a complete Rust implementation of the AG-UI protocol - an open standard for real-time AI agent-to-UI communication. This isn't just another chatbot interface; it's infrastructure that lets users see AI agents actually "thinking" through progressive responses, live tool execution, and multi-agent coordination. We're witnessing the biggest shift in cloud architecture since containers replaced VMs. The combination of WebAssembly, Rust, and true serverless is making Docker containers and Kubernetes clusters obsolete for AI agent workloads. I'll demonstrate a complete paradigm shift: modular AI agents that spin up in ~10ms, consume minimal memory, and cost pennies to run—all while being completely LLM-agnostic and framework-independent. The Architecture Revolution: - True Serverless: No more Docker containers waiting for requests. WASM agents cold-start in 10ms vs 1000ms+ for containers - Modular Agent Ecosystem: Each tool, agent, and interaction is now a composable module for the first time in AI infrastructure - Cost Transformation: 280KB binaries vs GB container images. Memory measured in KB, not GB. This changes startup economics completely - Self-Service Infrastructure: Startups can deploy sophisticated AI agents without managing Kubernetes clusters or container orchestration

- Event context: June 9th - LA AI Tinkerers Meetup & Demos — 2025-06-10 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_gG7geaVHf64

### [What Broke When I Tried to Vectorize 5M CIA Docs](https://nyc.aitinkerers.org/talks/rsvp_hazuF5wwMyU)

I’ll demo how I built a custom RAG pipeline on top of Cloudflare to ingest, embed, and serve 5M+ declassified government documents through an AI chat interface. The stack runs through Workers, queues, and Vectorize for semantic search—but building on Vectorize came with surprises. I’ll walk through my ingestion setup, how I chunked and embedded data at scale, and the technical issues I ran into: slowdowns from inserting vectors one-by-one, and serious bottlenecks from using timestamp metadata in milliseconds, which broke range queries. I’ll show the fixes I landed on after debugging with the Cloudflare team and reflect on the tradeoffs between Vectorize and tools like Pinecone for future scaling.

- Event context: Demos and Dim Sum with Deel and Apollo — 2025-06-03 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_hazuF5wwMyU

### [tldraw computer](https://london.aitinkerers.org/talks/rsvp_5hg8xdj4t8o)

In 2024, tldraw partnered with Google Deep Mind to create tldraw computer, an AI workflows and "natural language computing" experiment built on tldraw's infinite canvas. I'd love to present it to the AI Tinkerers community, talk about its development and share ideas for where it can go next.

- Event context: AI Tinkerers London - April Meetup — 2025-04-23 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_5hg8xdj4t8o

### [RAG Copilot: Big Data-powered solutions for rapid Information extraction](https://medellin.aitinkerers.org/talks/rsvp_1rdidJ3owc8)

Solution for Automatic Content Extraction from Large Data Volumes Using a RAG (Retrieval Augmented Generation) Model and AWS Serverless Architecture with a MapReduce Approach

- Event context: Lanzamiento de AI Tinkerers #1 — 2024-04-25 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_1rdidJ3owc8

### [Multiplayer AI on the Edge](https://london.aitinkerers.org/talks/rsvp_AY8-6GI3p7k)

There are two kinds of AI assistants: - Ones that you have to ask to do things. - Ones that watch everything you do in the background and act on your behalf for you I implemented Maggie Appleton's "AI Daemons" design concept, with her permission, from https://maggieappleton.com/lm-sketchbook#daemons. This demo shows how I built it, and deployed it to the edge using Cloudflare Workers platform.

- Event context: AI Tinkerers London July - RSVP REQUIRED — 2023-07-18 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_AY8-6GI3p7k

## Related Technologies

- [Durable Objects](https://aitinkerers.org/technologies/durable-objects) ([Markdown](https://aitinkerers.org/technologies/durable-objects.md)) — 8 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 219 public demos
- [Claude API](https://aitinkerers.org/technologies/claude-api) ([Markdown](https://aitinkerers.org/technologies/claude-api.md)) — 20 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 214 public demos
- [Cloudflare D1](https://aitinkerers.org/technologies/cloudflare-d1) ([Markdown](https://aitinkerers.org/technologies/cloudflare-d1.md)) — 3 public demos
- [Cloudflare Durable Objects](https://aitinkerers.org/technologies/cloudflare-durable-objects) ([Markdown](https://aitinkerers.org/technologies/cloudflare-durable-objects.md)) — 2 public demos
- [ElevenLabs](https://aitinkerers.org/technologies/elevenlabs) ([Markdown](https://aitinkerers.org/technologies/elevenlabs.md)) — 42 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [Playwright](https://aitinkerers.org/technologies/playwright) ([Markdown](https://aitinkerers.org/technologies/playwright.md)) — 32 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [R2](https://aitinkerers.org/technologies/r2) ([Markdown](https://aitinkerers.org/technologies/r2.md)) — 3 public demos
- [Rust](https://aitinkerers.org/technologies/rust) ([Markdown](https://aitinkerers.org/technologies/rust.md)) — 55 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [Vectorize](https://aitinkerers.org/technologies/vectorize) ([Markdown](https://aitinkerers.org/technologies/vectorize.md)) — 2 public demos
- [Agents SDK](https://aitinkerers.org/technologies/agents-sdk) ([Markdown](https://aitinkerers.org/technologies/agents-sdk.md)) — 2 public demos
- [AG-UI Protocol](https://aitinkerers.org/technologies/ag-ui-protocol) ([Markdown](https://aitinkerers.org/technologies/ag-ui-protocol.md)) — 2 public demos
- [AI Daemons](https://aitinkerers.org/technologies/ai-daemons) ([Markdown](https://aitinkerers.org/technologies/ai-daemons.md)) — 1 public demo