# fly Fly.io is a computing platform offering hardware-isolated virtual machines, deployment infrastructure, networking, and scaling. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## datasette-publish-fly 1.4 DevFeed: [datasette-publish-fly 1.4]() Original publisher: [Read original article]() Author: Simon Willison Published: 2026-09-11T02:58:52Z Content type: release Language: en Sources: [Simon Willison's Weblog]() Topics: [fly](), [App](), [bug]() Tags: [bug](), [datasette](), [datasette-1-542](), [deploy](), [fly](), [fly-40](), [https](), [release](), [volume]() ### AI overview Release notes for datasette-publish-fly 1.4. The release sets force_https=true in fly.toml, fixes a volume lookup bug, and adds compatibility with app-scoped deploy tokens. ### Source excerpt Release: datasette-publish-fly 1.4 Sets force_https=true in fly.toml. #31 Fix for Volume could not be found bug. #32 Compatible with app-scoped deploy tokens. #34 Tags: datasette, fly ## The Design & Implementation of Sprites DevFeed: [The Design & Implementation of Sprites]() Original publisher: [Read original article]() Published: 2026-01-14T00:00:00Z Content type: article Language: en Sources: [The Fly Blog]() Topics: [fly.io](), [fly](), [Cloud](), [Linux](), [Orchestration](), [ssh](), [Containers](), [Docker]() Tags: [cdn](), [close-to-users](), [cloud](), [cloud-computing](), [containers](), [cost](), [deploy-app-servers](), [docker](), [elixir](), [fly](), [fly-io](), [heroku-alternative](), [heroku-competitor](), [hosting](), [i](), [linux](), [networking](), [orchestration](), [platform](), [postgresql-clusters](), [scale](), [servers](), [ssh]() ### AI overview Fly.io's article introduces Sprites, disposable Linux virtual machines designed to start in seconds, provide root access and a durable 100GB filesystem, and automatically sleep when inactive. It explains the orchestration decisions behind the platform, including moving away from container images while retaining convenient, Docker-like workflows. ### Source excerpt We're Fly.io, and this is the place in the post where we'd normally tell you that our job is to take your containers and run them on our own hardware all around the world. But last week, we launched Sprites, and they don't work that way at all. Sprites are something new: Docker without Docker without Docker. This post is about how they work. Replacement-level homeowners buy boxes of pens and stick them in "the pen drawer". What the elites know: you have to think adversarially about pens. "The purpose of a system is what it does"; a household's is to uniformly distribute pens. Months from now, the drawer will be empty, no matter how many pens you stockpile. Instead, scatter pens every place you could possibly think to look for one -- drawers, ledges, desks. Any time anybody needs a pen, several are at hand, in exactly the first place they look. This is the best way I've found to articulate the idea of Sprites, the platform we just launched at Fly.io. Sprites are ball-point disposable computers. Whatever mark you mean to make, we've rigged it so you're never more than a second or two away from having a Sprite to do it with. Sprites are Linux virtual machines. You get root. They create in just a second or two: so fast, the experience of creating and shelling into one is identical to SSH'ing into a machine that already exists. Sprites all have a 100GB durable root filesystem. They put themselves to sleep automatically when inactive, and cost practically nothing while asleep. As a result, I barely feel the need to name my Sprites. Sometimes I'll just type sprite create dkjsdjk and start some task. People at Fly.io who use Sprites have dozens hanging around. There aren't yet many things in cloud computing that have the exact shape Sprites do: Instant creation No time limits Persistent disk Auto-sleep to a cheap inactive state This is a post about how we managed to get this working. We created a new orchestration stack that undoes some of the core decisions we made for Fly ## Make your ZeroGPU Spaces go brrr with ahead-of-time compilation DevFeed: [Make your ZeroGPU Spaces go brrr with ahead-of-time compilation]() Original publisher: [Read original article]() Author: Charles Bensimon; Sayak Paul; Linoy Tsaban; Apolinário from multimodal AI art Published: 2025-09-02T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [RAPIDS](), [GPU](), [fly](), [PyTorch](), [quantization](), [Open Source]() Tags: [compilation](), [gpu](), [guide](), [hugging-face](), [image-to-image](), [image-to-video](), [inference](), [latency](), [models](), [optimization](), [python](), [pytorch](), [quantization](), [spaces](), [text-to-image](), [zerogpu]() ### AI overview This tutorial explains how to use PyTorch ahead-of-time compilation in ZeroGPU Spaces. It covers faster model startup and inference, FP8 quantization, dynamic shapes, and the process-based GPU allocation model used by ZeroGPU, with reported speedups of 1.3x-1.8x on Flux, Wan, and LTX models. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Phoenix.new - The Remote AI Runtime for Phoenix DevFeed: [Phoenix.new - The Remote AI Runtime for Phoenix]() Original publisher: [Read original article]() Published: 2025-06-20T00:00:00Z Content type: article Language: en Sources: [The Fly Blog]() Topics: [phoenix](), [Elixir](), [Artificial Intelligence](), [Large Language Model](), [coding](), [fly.io](), [fly](), [browser](), [real-time](), [Visual Studio Code](), [Front end](), [JavaScript]() Tags: [agent](), [agents](), [ai](), [browser](), [cdn](), [close-to-users](), [coding](), [deploy-app-servers](), [docker](), [elixir](), [fly](), [fly-io](), [heroku-alternative](), [heroku-competitor](), [hosting](), [i](), [javascript](), [networking](), [phoenix](), [postgresql-clusters](), [real-time](), [servers](), [vscode]() ### AI overview Phoenix.new is a fully online coding agent tailored to Elixir and Phoenix. It runs in a browser-backed, isolated Fly Machine with shell access, a VSCode interface, and browser tools that let the agent inspect front-end changes and JavaScript state while building real-time collaborative applications. ### Source excerpt I'm Chris McCord, the creator of Elixir's Phoenix framework. For the past several months, I've been working on a skunkworks project at Fly.io, and it's time to show it off. I wanted LLM agents to work just as well with Elixir as they do with Python and JavaScript. Last December, in order to figure out what that was going to take, I started a little weekend project to find out how difficult it would be to build a coding agent in Elixir. A few weeks later, I had it spitting out working Phoenix applications and driving a full in-browser IDE. I knew this wasn't going to stay a weekend project. If you follow me on Twitter, you've probably seen me teasing this work as it picked up steam. We're at a point where we're pretty serious about this thing, and so it's time to make a formal introduction. World, meet Phoenix.new, a batteries-included fully-online coding agent tailored to Elixir and Phoenix. I think it's going to be the fastest way to build collaborative, real-time applications. Let's see it in action: What's Interesting About Phoenix.new First, even though it runs entirely in your browser, Phoenix.new gives both you and your agent a root shell, in an ephemeral virtual machine (a Fly Machine) that gives our agent loop free rein to install things and run programs -- without any risk of messing up your local machine. You don't think about any of this; you just open up the VSCode interface, push the shell button, and there you are, on the isolated machine you share with the Phoenix.new agent. Second, it's an agent system I built specifically for Phoenix. Phoenix is about real-time collaborative applications, and Phoenix.new knows what that means. To that end, Phoenix.new includes, in both its UI and its agent tools, a full browser. The Phoenix.new agent uses that browser "headlessly" to check its own front-end changes and interact with the app. Because it's a full browser, instead of trying to iterate on screenshots, the agent sees real page content and JavaScript state ## Provisioning Machines using MCPs DevFeed: [Provisioning Machines using MCPs]() Original publisher: [Read original article]() Published: 2025-05-07T00:00:00Z Content type: opinion Language: en Sources: [The Fly Blog]() Topics: [Provisioning](), [Model Context Protocol](), [fly.io](), [fly](), [Claude](), [cursor](), [GitHub]() Tags: [api](), [cdn](), [claude](), [close-to-users](), [copilot](), [cursor](), [deploy-app-servers](), [docker](), [elixir](), [fly](), [fly-io](), [github](), [heroku-alternative](), [heroku-competitor](), [hosting](), [i](), [mcps](), [networking](), [postgresql-clusters](), [provisioning](), [servers](), [terraform]() ### AI overview The author describes using MCP with Claude to create and manage Fly.io volumes, including deleting an unattached volume. The article argues that connecting LLMs to infrastructure tools can make application resource management more intuitive than using APIs, CLIs, or dashboards. ### Source excerpt Today's state of the art is K8S, Terraform, web based UIs, and CLIs. Those days are numbered. On Monday, I created my first fly volume using an MCP. For those who don't know what MCPs are, they are how you attach tools to LLMs like Claude or Cursor. I added support for fly volume create to fly mcp server, and it worked the first time. A few hours later, and with the assistance of GitHub Copilot, i added support for all fly volumes commands. This movie summary is from When Worlds Collide, by Nalaka Gunawardene I'm reminded of the memorable scene in the film Star Trek IV: The Voyage Home (1986). Chief Engineer Scotty, having time-travelled 200 years back to late 20th century San Francisco with his crew mates, encounters an early Personal Computer (PC). Sitting in front of it, he addresses the machine affably as "Computer!" Nothing happens. Scotty repeats himself; still no response. He doesn't realise that voice recognition capability hadn't arrived yet. Exasperated, he picks up the mouse and speaks into it: "Hello, computer?" The computer's owner offers helpful advice: "Just use the keyboard." Scotty looks astonished. "A keyboard?" he asks, and adds in a sarcastic tone: "How quaint!" A while later, I asked for a list of volumes for an existing app, and Claude noted that I had a few volumes that weren't attached to any machines. So I asked it to delete the oldest unattached volume, and it did so. Then it occurred to me to do it again; this time I captured the screen: A few notes: I could have written a program using the machines API, but that would have required some effort. I could have used flyctl directly, but to be honest, I would have had to use the documentation and a bit of copy/pasting of arguments. I could have navigated to a list of volumes for this application in the Fly.io dashboard, but there currently isn't any way to sort the list or delete a volume. Had those been in place, that would have been a reasonable alternative if that was something I was active ## Taming A Voracious Rust Proxy DevFeed: [Taming A Voracious Rust Proxy]() Original publisher: [Read original article]() Published: 2025-02-26T00:00:00Z Content type: article Language: en Sources: [The Fly Blog]() Topics: [Rust](), [fly](), [tracing](), [incident](), [Tokio](), [Containers](), [Network](), [virtual machines](), [HTTP](), [Monitoring](), [cpu]() Tags: [async](), [cdn](), [close-to-users](), [containers](), [cpu](), [deploy-app-servers](), [docker](), [elixir](), [fly](), [fly-io](), [heroku-alternative](), [heroku-competitor](), [hosting](), [http](), [i](), [incident](), [monitoring](), [network](), [networking](), [postgresql-clusters](), [rust](), [servers](), [tokio](), [tracing](), [virtual-machines]() ### AI overview The article investigates a recurring CPU and HTTP-error incident affecting Fly.io edge proxies. Profiling reveals unexpectedly high overhead in Rust tracing's Subscriber while the proxy handles largely idle asynchronous work, leading into a review of async Rust futures and Tokio execution. ### Source excerpt Here's a fun bug. The basic idea of our service is that we run containers for our users, as hardware-isolated virtual machines (Fly Machines), on hardware we own around the world. What makes that interesting is that we also connect every Fly Machine to a global Anycast network. If your app is running in Hong Kong and Dallas, and a request for it arrives in Singapore, we'll route it to HKG. Our own hardware fleet is roughly divided into two kinds of servers: edges, which receive incoming requests from the Internet, and workers, which run Fly Machines. Edges exist almost solely to run a Rust program called fly-proxy, the router at the heart of our Anycast network. So: a week or so ago, we flag an incident. Lots of things generate incidents: synthetic monitoring failures, metric thresholds, health check failures. In this case two edge tripwires tripped: elevated fly-proxy HTTP errors, and skyrocketing CPU utilization, on a couple hosts in IAD. Our incident process is pretty ironed out at this point. We created an incident channel (we ❤ Rootly for this, seriously check out Rootly, an infra MVP here for years now), and incident responders quickly concluded that, while something hinky was definitely going on, the platform was fine. We have a lot of edges, and we've also recently converted many of our edge servers to significantly beefier hardware. Bouncing fly-proxy clears the problem up on an affected proxy. But this wouldn't be much of an interesting story if the problem didn't later come back. So, for some number of hours, we're in an annoying steady-state of getting paged and bouncing proxies. While this is happening, Pavel, on our proxy team, pulls a profile from an angry proxy. So, this is fuckin' weird: a huge chunk of the profile is dominated by Rust tracing's Subscriber. But that doesn't make sense. The entire point of Rust tracing, which generates fine-grained span records for program activity, is that entering and exiting a span is very, very fast. If the mere ## Deploying applications to Fly.io without Docker DevFeed: [Deploying applications to Fly.io without Docker]() Original publisher: [Read original article]() Author: Harsh Shandilya Published: 2024-10-05T06:30:00Z Content type: tutorial Language: en Sources: [Posts on Harsh Shandilya]() Topics: [fly.io](), [fly](), [Skopeo](), [Docker Image](), [docker registry](), [Nix](), [Command-line interface](), [Deployment]() Tags: [cli](), [deployment](), [docker](), [docker-image](), [docker-registry](), [fly](), [fly-io](), [nix](), [oci-registry](), [skopeo]() ### AI overview A guide to deploying applications on Fly.io without installing Docker locally. It explains how to use Nix to build an OCI image and Skopeo to copy the image archive to Fly.io's registry before deployment. ### Source excerpt A quick guide to deploying apps to Fly.io without a local Docker installation ## We're Cutting L40S Prices In Half DevFeed: [We're Cutting L40S Prices In Half]() Original publisher: [Read original article]() Published: 2024-08-15T00:00:00Z Content type: news Language: en Sources: [The Fly Blog]() Topics: [fly.io](), [GPU](), [fly](), [Inference](), [Cloud](), [Artificial Intelligence](), [Generative AI](), [NeMo](), [Nvidia](), [stable-diffusion](), [NVLink]() Tags: [ai](), [cdn](), [close-to-users](), [cloud](), [deploy-app-servers](), [docker](), [elixir](), [fly](), [fly-io](), [generative-ai](), [gpu](), [hardware](), [heroku-alternative](), [heroku-competitor](), [hosting](), [i](), [inference](), [nemo](), [networking](), [nvidia](), [nvlink](), [postgresql-clusters](), [servers](), [stable-diffusion]() ### AI overview Fly.io announces that it has cut the price of NVIDIA L40S GPUs to $1.25 per hour. The article explains that customers most often choose the less powerful A10 for inference and mid-sized generative AI workloads such as Mistral Nemo and Stable Diffusion, while Fly.io's earlier GPU strategy focused on more demanding ideas involving A100 partitioning, NVLink clusters, and training. ### Source excerpt We're Fly.io, a new public cloud with simple, developer-friendly ergonomics. And as of today, cheaper GPUs. Try it out; you'll be deployed in just minutes. We just lowered the prices on NVIDIA L40s GPUs to $1.25 per hour. Why? Because our feet are cold and we burn processor cycles for heat. But also other reasons. Let's back up. We offer 4 different NVIDIA GPU models; in increasing order of performance, they're the A10, the L40S, the 40G PCI A100, and the 80G SXM A100. Guess which one is most popular. We guessed wrong, and spent a lot of time working out how to maximize the amount of GPU power we could deliver to a single Fly Machine. Users surprised us. By a wide margin, the most popular GPU in our inventory is the A10. The A10 is an older generation of NVIDIA GPU with fewer, slower cores and less memory. It's the least capable GPU we offer. But that doesn't matter, because it's capable enough. It's solid for random inference tasks, and handles mid-sized generative AI stuff like Mistral Nemo or Stable Diffusion. For those workloads, there's not that much benefit in getting a beefier GPU. As a result, we can't get new A10s in fast enough for our users. If there's one thing we've learned by talking to our customers over the last 4 years, it's that y'all love a peek behind the curtain. So we're going to let you in on a little secret about how a hardware provider like Fly.io formulates GPU strategy: none of us know what the hell we're doing. If you had asked us in 2023 what the biggest GPU problem we could solve was, we'd have said "selling fractional A100 slices". We burned a whole quarter trying to get MIG, or at least vGPUs, working through IOMMU PCI passthrough on Fly Machines, in a project so cursed that Thomas has forsworn ever programming again. Then we went to market selling whole A100s, and for several more months it looked like the biggest problem we needed to solve was finding a secure way to expose NVLink-ganged A100 clusters to VMs so users could run train ## Deploy Turso embedded replicas to Fly, Akamai, Koyeb, Railway, & Render. DevFeed: [Deploy Turso embedded replicas to Fly, Akamai, Koyeb, Railway, & Render.]() Original publisher: [Read original article]() Author: James Sinkala Published: 2024-04-11T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [Embedded Replicas](), [Turso](), [fly](), [Cloud](), [SQLite](), [libSQL]() Tags: [akamai](), [application-development](), [cloud](), [databases](), [deployment-guides](), [devices](), [documentation](), [embedded](), [embedded-replicas](), [fly](), [libsql](), [offline](), [platform](), [sdks](), [servers](), [sqlite](), [turso]() ### AI overview This article describes deploying Turso embedded replicas on Fly, Akamai, Koyeb, Railway, and Render. It also explains Turso's SQLite-based architecture, including querying databases over the network, syncing with devices and servers, offline support, and the distinction between database files and processes. ### Source excerpt Deploy Turso embedded replicas on your favourite platform. ## Fly Postgres, managed by Supabase DevFeed: [Fly Postgres, managed by Supabase]() Original publisher: [Read original article]() Author: Inian Parameshwaran; Paul Copplestone Published: 2023-12-15T07:00:00Z Content type: release Language: en Sources: [Supabase Blog]() Topics: [Databases](), [fly](), [fly.io](), [Supabase](), [Latency](), [Firecracker](), [API](), [GraphQL](), [observability](), [Replication]() Tags: [api](), [edge-computing](), [firecracker](), [fly](), [fly-io](), [graphql](), [latency](), [observability](), [postgres](), [recovery](), [release](), [replication](), [testing]() ### AI overview Supabase and Fly.io are launching Fly Postgres, a managed Postgres service deployed across Fly.io's edge locations. It includes extensions, pgvector support, connection pooling, backups, point-in-time recovery, branching, observability, migrations, a dashboard, and automatically generated REST and GraphQL APIs. The service is being progressively rolled out to testers. ### Source excerpt A managed Postgres offering developed by Supabase and Fly.io ## How to run Remark42 on Fly.io DevFeed: [How to run Remark42 on Fly.io]() Original publisher: [Read original article]() Author: andreacorbellini Published: 2023-09-19T02:12:00Z Content type: tutorial Language: en Sources: [Andrea Corbellini]() Topics: [fly.io](), [fly](), [cloud-infrastructure](), [Containers](), [Command-line interface](), [backups]() Tags: [backups](), [blog](), [cloud](), [command-line](), [containers](), [fly-io](), [how-to](), [storage]() ### AI overview A tutorial explaining how to set up Remark42 comments on Fly.io. It describes a single-machine, single-volume deployment, notes that Remark42 stores comments in one file without distributed replication, and recommends periodic backups because of the risk of permanent data loss. ### Source excerpt As I wrote on my previous post, I recently switched from Disqus to Remark42 for the comments on my blog. Here I will explain how I set it up on Fly.io. Overview The setup that I ended up with looks like the following: Something to note about this setup is that the "machine" (more on that later) and the storage volume are both ... ## Customer Workflows: Building a loyalty program with Temporal DevFeed: [Customer Workflows: Building a loyalty program with Temporal]() Original publisher: [Read original article]() Author: Fitz Published: 2023-08-03T17:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [Actor](), [fly](), [Code](), [Framework](), [GitHub](), [Go](), [Java](), [Python]() Tags: [actor](), [customers](), [github](), [go](), [how-to](), [java](), [loyalty-account](), [python](), [workflows]() ### AI overview This tutorial explains how Temporal Workflows can represent Actors through a customer loyalty account example. It reviews the Actor Model's requirements--message handling, creating Actors, and maintaining state--and describes how a loyalty account tracks points and rewards. The article includes Go, Java, and Python implementations. ### Source excerpt Discover how Temporal optimizes customer workflows in loyalty programs, managing actors and tasks efficiently to enhance customer engagement and retention. ## Fly.io makes infrastructure easy for developers DevFeed: [Fly.io makes infrastructure easy for developers]() Original publisher: [Read original article]() Author: Pekka Enberg Published: 2022-09-22T00:00:00Z Content type: opinion Language: en Sources: [Turso Blog]() Topics: [fly.io](), [fly](), [cloud-infrastructure](), [Amazon EKS](), [Turso](), [libSQL]() Tags: [backend-development](), [chiselstrike](), [cloud](), [developers](), [fly](), [fly-io](), [infrastructure](), [infrastructure-as-code](), [libsql](), [turso]() ### AI overview The article presents Fly.io as a developer-friendly way to simplify infrastructure and application deployment, contrasting it with the complexity of EBS volumes and EKS storage classes. It also notes that the referenced Turso material is outdated and describes newer Turso capabilities and SDKs. ### Source excerpt Fly.io feels like it's going to make infrastructure easy for developers. No more fighting with EBS volumes or EKS storage classes to get your app deployed. ## Optimize Nginx for performance DevFeed: [Optimize Nginx for performance]() Original publisher: [Read original article]() Author: Tom Published: 2016-01-14T00:00:00Z Content type: tutorial Language: en Sources: [Tomasz Gągor]() Topics: [nginx](), [Caching](), [fly](), [TLS (Transport Layer Security)](), [HTTP]() Tags: [caching](), [compression](), [grafana](), [https-configuration](), [linux](), [nginx](), [performance](), [tls]() ### AI overview A practical guide to improving Nginx performance through caching static and dynamic content, compressing web assets, and optimizing SSL/TLS connections. It emphasizes testing and monitoring because optimization techniques may not suit every deployment. ### Source excerpt There are many possible real life cases and not all optimization technics will be suitable for you but I hope it will be a good starting place. Also you shouldn't copy paste examples with faith that they will make your server fly 😃 You have to support your decisions with excessive tests and help of monitoring system (ex. Grafana ). Cache static and dynamic content Setting caching static and dynamic content strategy may offload your server from additional load from repetitive downloads of same, rarely updated files. This will make your site to load faster for frequent visitors.