Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Virtual Machine = Real Collaboration
Discover how a shared virtual machine setup for code models enhances team productivity and accuracy, enabling seamless collaboration, testing, and deployment without inconsistencies.
One source of truth - a secure, team-shared, VM OpenCode setup.
My team and I have unlocked a step change in productivity and, more importantly, accuracy by moving our OpenCode (you might use Claude Code, Codex, Hermes, whatever) onto a virtual server. The groundbreaking part, for us, is (1) the shared context - the RULES, DEVLOG, README, and similar files, and (2) the ability for anyone to immediately spin up live code in a usable environment to evaluate, test, QA, demo, etc. All without the subtle bits of code ‘fun’ where each person does things 10% differently, causing issues and rework.
Generated 2 months ago
To address the challenges of collaborative software development, such as inconsistent coding styles and compounding technical debt, the speaker developed an AI-driven development environment hosted on a virtual machine. Operating via a browser, app, or Discord, the system utilizes specialized agents to automatically write, type-check, and test code according to strict team guidelines. During the live demo, the speaker submitted a feature ticket to the bot, which successfully modified a TypeScript route-planning interface and relaunched the development environment in real time. The audience learns how structured, cloud-based AI agents can automate QA, enforce coding standards, and streamline development workflows.
View full transcript
- OpenCodeOpenCode is the open-source AI coding agent (CLI tool), integrating LLMs like GPT-5 and Claude Sonnet 4 directly into the terminal for fast, context-aware development.OpenCode is the open-source AI coding agent, built for terminal-first developers who demand speed and privacy. It connects your local files, Git history, and a choice of LLMs (e.g., OpenAI's GPT-5 Nano, Anthropic's Claude Sonnet 4) to execute complex tasks directly from the command line . The tool bypasses IDE and browser dependencies, allowing developers to triage issues, fix errors, or implement features with commands like `opencode fix error in main.go` . With over 26,000 GitHub stars by October 2025, OpenCode delivers a secure, context-aware coding partner that keeps your code local and your workflow efficient .
- CodexCodex is OpenAI's autonomous AI software engineering agent: it executes full development tasks in a sandboxed cloud environment.Codex is the advanced, cloud-based software engineering agent from OpenAI, built on a specialized model like `codex-1` (a fine-tuned version of `o3`). It operates on an asynchronous delegation model, allowing developers to assign complete tasks—not just receive suggestions—via the ChatGPT interface. The agent works independently in a secure, isolated cloud container provisioned with the user's GitHub repository and environment. It reads code, writes new features, fixes bugs, runs tests, and drafts Pull Requests (PRs) for review, significantly accelerating the development lifecycle. Access is provided through ChatGPT Plus, Pro, and Enterprise plans.
- GitHubHost Git repositories and enable massive-scale collaboration (pull requests, issue tracking) for over 100 million developers.GitHub is the world's dominant web-based platform for Git repository hosting and collaborative software development. Built on Linus Torvalds' Git version control system, the platform facilitates 'social coding' by providing essential tools like pull requests, forking, and issue tracking. It currently serves over 100 million developers, managing a massive ecosystem of public and private codebases. Microsoft acquired the company in 2018 for $7.5 billion, solidifying its role as the central hub for open-source and enterprise-level version control.
- Google Cloud PlatformGCP delivers Google's global infrastructure (Compute Engine, BigQuery) for secure, scalable cloud solutions and AI/ML innovation.Google Cloud Platform (GCP) provides the core infrastructure and services for modern digital transformation. The platform leverages Google's global network, spanning 39 regions and 118 zones, to host critical workloads securely. Key services include Compute Engine (IaaS), Google Kubernetes Engine (GKE) for container orchestration, and BigQuery (serverless data warehouse) for petabyte-scale analytics. GCP integrates advanced AI/ML capabilities via Vertex AI, allowing developers to build and deploy models fast. Security is paramount: the platform uses Google's multi-layered security model, protecting data and applications with zero-trust principles. New customers can utilize the free tier and $300 in credits to deploy their next project.
- TailscaleTailscale builds a secure, peer-to-peer mesh network using WireGuard to connect your devices and workloads without manual firewall configuration.Tailscale replaces legacy VPNs with a zero-trust architecture that just works. It uses the WireGuard protocol to establish encrypted, direct connections between nodes (laptops, servers, or cloud instances) regardless of physical location or complex NAT settings. You manage access through a central control plane using your existing identity provider (Google, Microsoft, or Okta) and define granular permissions via ACLs as code. Features like MagicDNS provide stable hostnames for every device, while Tailscale Funnel and Exit Nodes offer flexible routing for public sharing or secure internet egress. It is a lightweight, high-performance solution for 20,000+ companies looking to simplify networking across multi-cloud and edge environments.
Related talks
More from the community
Coding is Solved. Next Up: Figure Out How to Plan
Seattle
Discover how to manage AI-generated plans and code reviews efficiently. This talk explores building an agent-native Google Docs…
The IDE is Dead. Vulcan Ships Our Code Now.
London
See how an AI dev system orchestrates Claude agents to build, test, and autonomously fix CI failures, managing…
Make Vibe Coding Actually Ship
Manchester NH
See how a structured loop, separating ideation, specification, and execution with AI tools, turns AI ideas into working…
Dev tools are all you need
Seattle
Explore Maibook, a desktop app using AI agents personalized from your file system. See customized dev tools for…
Juggle 10+ projects in parallel without getting overwhelmed
Atlanta
Learn how to manage 15+ parallel AI projects using tmux, prompt-triggered monitoring, and a local dashboard, leveraging AI…
AI that launches, runs and owns a software company
Boston
See how an AI can launch and run a software company using Tokenized IP Licenses, managing research, promotion,…
Compose Email
Loading recent emails...