# Durable Objects Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/durable-objects
> Markdown URL: https://aitinkerers.org/technologies/durable-objects.md
> Technology record last updated: 2026-03-03T15:36:21Z
> Generated: 2026-09-22T10:52:23Z

Durable Objects deliver globally unique, single-threaded compute instances with strongly consistent, transactional storage, enabling stateful serverless applications.

Durable Objects (DOs) are a core primitive of the Cloudflare Workers platform: they combine compute with isolated, persistent storage. Each DO instance is globally addressable by a unique ID, guaranteeing that only one instance of the object executes at any given time, which completely eliminates race conditions and the need for distributed locks. This single-threaded Actor model simplifies building complex stateful systems. Use DOs for real-time coordination: think collaborative editing, multiplayer game sessions, or managing millions of individual user workspaces. The attached storage is fast, transactional, and strongly consistent, supporting up to 10 GB of data or a SQLite backend, all without managing any infrastructure.

- Official technology site: https://developers.cloudflare.com/durable-objects/
- Public AI Tinkerers demos and talks: 8
- Result page: 1 of 1

## Recent Public Talks and Demos

### [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

### [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

### [Durable Vibes](https://singapore.aitinkerers.org/talks/rsvp_fUUim-CSXws)

A live demo of multiplayer vibe coding, made possible with Cursor SDK (Composer) & Durable Objects!

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

### [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

### [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

### [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

### [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

- [Cloudflare Workers](https://aitinkerers.org/technologies/cloudflare-workers) ([Markdown](https://aitinkerers.org/technologies/cloudflare-workers.md)) — 22 public demos
- [R2](https://aitinkerers.org/technologies/r2) ([Markdown](https://aitinkerers.org/technologies/r2.md)) — 3 public demos
- [AI Daemons](https://aitinkerers.org/technologies/ai-daemons) ([Markdown](https://aitinkerers.org/technologies/ai-daemons.md)) — 1 public demo
- [AI Gateway](https://aitinkerers.org/technologies/ai-gateway) ([Markdown](https://aitinkerers.org/technologies/ai-gateway.md)) — 2 public demos
- [Browser Rendering](https://aitinkerers.org/technologies/browser-rendering) ([Markdown](https://aitinkerers.org/technologies/browser-rendering.md)) — 1 public demo
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 174 public demos
- [Claude API](https://aitinkerers.org/technologies/claude-api) ([Markdown](https://aitinkerers.org/technologies/claude-api.md)) — 21 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 215 public demos
- [Cloudflare](https://aitinkerers.org/technologies/cloudflare) ([Markdown](https://aitinkerers.org/technologies/cloudflare.md)) — 17 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
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [D1](https://aitinkerers.org/technologies/d1) ([Markdown](https://aitinkerers.org/technologies/d1.md)) — 1 public demo
- [Deepgram Flux](https://aitinkerers.org/technologies/deepgram-flux) ([Markdown](https://aitinkerers.org/technologies/deepgram-flux.md)) — 2 public demos
- [Edge computing](https://aitinkerers.org/technologies/edge-computing) ([Markdown](https://aitinkerers.org/technologies/edge-computing.md)) — 6 public demos
- [GPT](https://aitinkerers.org/technologies/gpt) ([Markdown](https://aitinkerers.org/technologies/gpt.md)) — 26 public demos
- [Llama 3](https://aitinkerers.org/technologies/llama-3) ([Markdown](https://aitinkerers.org/technologies/llama-3.md)) — 38 public demos
- [Modal](https://aitinkerers.org/technologies/modal) ([Markdown](https://aitinkerers.org/technologies/modal.md)) — 14 public demos