Sign in

ngrok

@ngrok.com
375 followers 14 following 95 posts

One gateway for all your traffic. Service status available at status.ngrok.com.

PostsRepliesMedia
Reposted by ngrok
fry69 @fry69.dev · 10/09/2026
Highly recommended blog and video by @anniesexton.com about the relation between compression algorithms and large language model token prediction. -> ngrok.com/blog/compres...
ngrok.com
Compression is prediction | ngrok blog
Compression and LLMs are trying to solve the exact same problem: predicting what comes next. Learn the fundamentals of compression and how better prediction leads to better shrinkage.
161
Reposted by ngrok
Annie Sexton @anniesexton.com · 09/09/2026
I made a video about the compression article, it has animations, go watch it and admire my sick new studio.
2245
ngrok @ngrok.com · 09/09/2026
The best compressors are... LLMs? Compression and language modeling share a job: predicting what comes next. @anniesexton.com shows how those predictions become fewer bits, and why gzip still gets to keep its all-important job. ↓ www.youtube.com/watch?v=HkUy...
youtube.com
The best compressors are...LLMs?
YouTube video by ngrok
0121
ngrok @ngrok.com · 02/09/2026
Yeah, no. You shouldn't roll your own. Connect frontier providers and self-hosted models through one managed gateway ↓ ngrok.ai
ngrok.ai
Never bet on one model — ngrok.ai
Route, secure, and manage traffic to any LLM—cloud or local—with one unified platform. Monitor usage, optimize costs, and keep your AI products online.
000
ngrok @ngrok.com · 02/09/2026
GOPHRS is here. AI gateway migration is mandatory. The arch is final (as in "no more feature requests" final). Please watch the full architecture briefing before submitting questions. www.youtube.com/watch?v=UVe1...
youtube.com
GOPHRS is here. AI gateway migration is mandatory.
YouTube video by ngrok
131
Reposted by ngrok
Marcus Noble @averagemarcus.bsky.social · 25/08/2026
This post from Sam Rose is absolutely fantastic! 💙 A real deep dive into Kubernetes probe with amazing interactive demos, advice and even a bug discovered in Kubernetes! 🤯 ngrok.com/blog/probes
ngrok.com
How Kubernetes probes work | ngrok blog
Learn how probes work interactively on simulated Kubernetes clusters running in your browser.
0165
Reposted by ngrok
Sean Killeen @seankilleen.com · 20/08/2026
Phenomenal article from @samwho.dev at @ngrok.com on #kubernetes probes ngrok.com/blog/probes With interactive visualizations! Really nicely done. I learned a ton.
ngrok.com
How Kubernetes probes work | ngrok blog
Learn how probes work interactively on simulated Kubernetes clusters running in your browser.
021
Reposted by ngrok
Sam Rose @samwho.dev · 19/08/2026
Impossible to overstate how much of my soul is imbued into this post. I wanted to push the boundaries of the web as an education platform. Why _shouldn’t_ we run Kubernetes in the browser to demonstrate for-real what happens, and let you influence it? Hope you love it. 🫶
89218
ngrok @ngrok.com · 19/08/2026
Stick around for the probe playground at the end to dial in the right setup for your own pods ↓ ngrok.com/blog/probes
ngrok.com
How Kubernetes probes work | ngrok blog
Learn how probes work interactively on simulated Kubernetes clusters running in your browser.
0122
ngrok @ngrok.com · 19/08/2026
What do a port of Kubernetes to TypeScript and a high-priority bug in the kubelet have in common? They both feature in @samwho.dev's guide to probing, out now. We're experimenting with what next-generation k8s education looks like, and we hope you love it.
1466
ngrok @ngrok.com · 13/08/2026
Thanks so much for pointing this out, just merged a fix to make the feed discoverable from anywhere on the site!
120
ngrok @ngrok.com · 13/08/2026
This is really great feedback. Just pushed out a little fix to add "Topics: " before the tags to help clarify. Last thing I want is for Annie's incredibly hard research and creative work on this article to be thought of AI generated.
000
Reposted by ngrok
Pieter van der Westhuizen 💙 @mythicalmanmoth.com · 12/08/2026
One of the best explained and clearly written pieces I've read in a long time. Love the interactive examples. Very cool. Nice one @anniesexton.com !
011
ngrok @ngrok.com · 11/08/2026
Cosigned.
000
ngrok @ngrok.com · 11/08/2026
It's truly the dream team.
070
Reposted by ngrok
Annie Sexton @anniesexton.com · 11/08/2026
This is the coolest article I've ever written. Genuinely. All of you should read it.
1329545
ngrok @ngrok.com · 11/08/2026
Check it out ↓ ngrok.com/blog/compres...
ngrok.com
Compression is prediction | ngrok blog
Compression and LLMs are trying to solve the exact same problem: predicting what comes next. Learn the fundamentals of compression and how better prediction leads to better shrinkage.
2549
ngrok @ngrok.com · 11/08/2026
Compression and LLMs are trying to solve the exact same problem: predicting what comes next. @anniesexton.com's interactive essay walks us through the basics of compression to reveal its surprising overlap with every language model you've ever used.
513225
ngrok @ngrok.com · 05/08/2026
You should be able to send inference: → to any public provider → privately to models you self-host → to any number of fallbacks → with full access control and observability built in ngrok.ai is live on Product Hunt today ↓ www.producthunt.com/products/ngr...
ngrok.ai
One gateway, every model — ngrok.ai
Route, secure, and manage traffic to any LLM—cloud or local—with one unified platform. Monitor usage, optimize costs, and keep your AI products online.
010
ngrok @ngrok.com · 30/07/2026
Poke at the live demo: webernetes-demo.ngrok.app Take a gander at the open-source project: github.com/ngrok/webern...
webernetes-demo.ngrok.app
webernetes demo
A browser-friendly simulation of Kubernetes components.
010
ngrok @ngrok.com · 30/07/2026
"You need four of this pod... how hard can that be?" — @samwho.dev Turns out it's several thousand lines of code hard. Part 4 of our video series on his Kubernetes-in-the-browser project tiptoes through that and other footguns ↓ youtu.be/y4XAOcCT9dY
youtu.be
Webernetes: How we got Kubernetes running in the browser
YouTube video by ngrok
131
Reposted by ngrok
ScyllaDB @scylladb.com · 28/07/2026
💡 Tuesday tech tip: At our free & virtual #P99CONF, @ngrok.com's Sam Rose will dive into the mathematical process applied to models to make them smaller and introduce our audience to tools that gauge how much a quantized model differs from its original. www.p99conf.io?latest_sfdc_... #ScyllaDB
041
ngrok @ngrok.com · 13/07/2026
Validating JWTs, restricting IPs, and running a WAF on your ngrok endpoints just got 10x cheaper. Traffic Policy is now $0.10 per 100k TPUs, down from $1. OAuth didn't get cheaper. It was already free. ↓ ngrok.com/blog/pricing...
ngrok.com
Traffic Policy is now 10x cheaper, and idle custom domains are free | ngrok blog
Traffic Policy pricing drops by 10x, custom domains move to active-only billing, and Endpoint Pooling now bills per active endpoint. Here's what changed and why.
000
ngrok @ngrok.com · 09/07/2026
Part 1: youtube.com/watch?v=xckI... Part 2: youtube.com/watch?v=wRSyz0 _bhPI Of course, webernetes is open source: github.com/ngrok/webern...
github.com
GitHub - ngrok/webernetes: Kubernetes in the browser.
Kubernetes in the browser. Contribute to ngrok/webernetes development by creating an account on GitHub.
030
ngrok @ngrok.com · 09/07/2026
The next interactive essay from @samwho.dev is about k8s probes, but even starting it took… 90k lines of TypeScript. Here's webernetes episode 3: the first demo of a cluster in a browser tab. Deployment controllers due in 3 days, when Sam's summer holiday starts ↓ www.youtube.com/watch?v=gxo3...
youtube.com
The demo that proves Kubernetes can run in the browser
YouTube video by ngrok
171
ngrok @ngrok.com · 01/07/2026
One flat fee: $0.05 per million tokens ,with your inference billed on top. Buy credits as you go. Full writeup → ngrok.com/blog/new-ngr... Docs → ngrok.com/docs/ai-gate...
ngrok.com
The new ngrok.ai | ngrok blog
The ngrok AI Gateway is now app.ngrok.ai. One key, one URL to access any model, including the ones you run yourself, with access controls and per-call cost visibility.
000
ngrok @ngrok.com · 01/07/2026
When you route to a local model, it's full private connectivity: no publicly addressable URLs, no public IPs to allowlist, or ports to open, wherever you've got those GPUs humming. Works with Ollama, vLLM, LM Studio, and the neoclouds, too.
100
ngrok @ngrok.com · 01/07/2026
One baseURL change and an access key gets you: → routing to every model, even dedicated ones on AWS, Azure, etc → automatic failover + retries when a model slows or fails → scoped keys per app → token, latency, and cost visibility by app, dev, and model
100
ngrok @ngrok.com · 01/07/2026
You can now call models running on your own hardware through a hosted AI gateway. Privately, with one command: `ngrok http 8000 --url https:⁠//vllm.internal` Plus all the public models you know and love. ↓ ngrok.ai
ngrok.ai
Route, Secure & Manage Any LLM with ngrok AI Gateway
Route, secure, and manage traffic to any LLM—cloud or local—with one unified platform. Monitor usage, optimize costs, and keep your AI products online.
110
Reposted by ngrok
Sam Rose @samwho.dev · 30/06/2026
I promise this is my last post this week sharing work stuff but we’ve condensed a bunch of new stuff @ngrok.com can do into a 6 and a half minute video! This is for the folks that know how to run `ngrok http 8080` but haven’t ventured further into the product than that. 🫶 youtu.be/trXqyNXJa1k?...
youtu.be
This is ngrok in 2026
YouTube video by ngrok
0103
ngrok @ngrok.com · 30/06/2026
Yes, ngrok gives localhost a public URL. It's also load-bearing production infrastructure. Reach into customer networks. Put every bit of ingress behind one front door. Run one gateway for devices, APIs, and LLMs. Here's what ngrok really is today ↓ www.youtube.com/watch?v=trXq...
youtube.com
This is ngrok in 2026
YouTube video by ngrok
000
ngrok @ngrok.com · 30/06/2026
Yeahhh, that was my suspicion, too, unfortunately. I hope you can at least give the links a bookmark for later!
010
ngrok @ngrok.com · 30/06/2026
What kind of error do you see, if any? These both appear to be fully functional for us. Can you access *any* ngrok.com or ngrok.app property?
100
Reposted by ngrok
Sam Rose @samwho.dev · 30/06/2026
Inviting controversy with this take, which is outside of my comfort zone, but I do stand by it. You can generate good quality code with LLMs, it “just” requires a tonne of human oversight and automated guard rails. Got a week off then I’ll be building my first proper post with webernetes. Stoked.
9794
ngrok @ngrok.com · 30/06/2026
Those dots moving around a webpage? Real (enough) pods sending each other requests over a simulated network, all in your browser. Hit pause and the whole cluster freezes, because it runs on a fake clock. Go poke at the demo for yourself: webernetes-demo.ngrok.app
030
ngrok @ngrok.com · 30/06/2026
Our own @samwho.dev ported Kubernetes to the browser. Like a real flippin' cluster with lifecycles, DNS, and a simulated network. It's ~100k lines of TypeScript, almost all written by LLMs, but with every line reviewed by hand to keep it slop-free ↓ ngrok.com/blog/i-porte...
ngrok.com
I ported Kubernetes to the browser | ngrok blog
Almost 100,000 lines of LLM-generated code in 2 months, and none of it is slop.
3274
ngrok @ngrok.com · 18/06/2026
Sam has also talked at length with our very own Ryan on how the build has come together, the tools he's used, and all the k8s internals he *had no idea about*. www.youtube.com/watch?v=wRSy...
youtube.com
Kubernetes...in the browser? Part II
YouTube video by ngrok
010
ngrok @ngrok.com · 18/06/2026
Yup, @samwho.dev is a wild one for this. But we want to teach the invisible layers of modern software in ways grounded in reality. Ways that'll last for a long, long time. Sometimes that means 100k lines of TypeScript just to earn the right to start telling the story at all.
110
ngrok @ngrok.com · 03/06/2026
53k lines of TypeScript later, and counting, it's working. When it's ready for prime time, he'll open source it all, too. All to make k8s education "unlike anything anyone has ever seen." Watch episode 1 of the build 👉 www.youtube.com/watch?v=xckI...
youtube.com
I'm making a Kubernetes cluster that runs in the browser
YouTube video by ngrok
091
ngrok @ngrok.com · 03/06/2026
Our very own @samwho.dev decided the only honest way to explain how Kubernetes probes work, using his signature interactive essay style, was to build himself a cluster. In the browser. 👇
1260
ngrok @ngrok.com · 01/04/2026
Thanks for the head's up. We're aware of the issue and we've got folks get the binaries back into the channels where they don't cache it, like homebrew. Downloading the binary directly from our downloads page still does wok. Sorry for the troubles! github.com/ngrok/homebr...
github.com
brew install ngrok/ngrok/ngrok is not working · Issue #76 · ngrok/homebrew-ngrok
I am having below error ==> Fetching downloads for: ngrok/ngrok/ngrok ✘ Cask ngrok (3.37.3) Error: Download failed on Cask 'ngrok' with message: Download failed: https://bin.ngrok.com/a/5mfSNpNhBZC...
300
ngrok @ngrok.com · 30/03/2026
Set it up in the dashboard or API. Currently free on pay-as-you-you plans. ngrok.com/blog/2026-03...
ngrok.com
Pin your traffic to specific regions | ngrok blog
Your traffic, your rules. Route ngrok domains through specific geographic PoPs for compliance, security, or just because you want to.
000
ngrok @ngrok.com · 30/03/2026
We gave ngrok domains a `resolves_to` property and, what do you know, made the *routing* part of data residency a one-click. Pin your traffic to specific PoPs so European data stays in Europe, then rearrange the whole thing tomorrow if you want.
200
ngrok @ngrok.com · 26/03/2026
Expose local apps and APIs to the internet with your coding agent and our new `expose-localhost` skill. Then ask it to add in OAuth, OWASP protection, rate limits, and more if you're feeling plucky. $ npx skills add ngrok/agent-skills github.com/ngrok/agent-...
github.com
GitHub - ngrok/agent-skills: Official repository for ngrok agent skills.
Official repository for ngrok agent skills. Contribute to ngrok/agent-skills development by creating an account on GitHub.
1531
ngrok @ngrok.com · 25/03/2026
Quantization can make an LLM 4x smaller and 2x faster, with barely any quality loss. But what *is* it? @samwho.dev crafted a beautiful interactive essay explaining it from first principles, aimed at coders, not mathematicians. ngrok.com/blog/quantiz...
ngrok.com
Quantization from the ground up | ngrok blog
A complete guide to what quantization is, how it works, and how it's used to compress large language models
052
Reposted by ngrok
Sam Rose @samwho.dev · 25/03/2026
I spent 2 months learning about quantization and am extremely proud of the post I've written about it. I think these are some of the nicest visuals I've ever made, and I love how this compression technique invented in 1898 is being used on the bleeding edge in 2026. ngrok.com/blog/quantiz...
ngrok.com
Quantization from the ground up | ngrok blog
A complete guide to what quantization is, how it works, and how it's used to compress large language models
1425155
ngrok @ngrok.com · 02/03/2026
Route between OpenAI and Anthropic with one API key without an account for either. ngrok's AI Gateway now has its own API keys and prepaid credits. One key covers both, and you can just set your model to "ngrok/auto" if you don't even want to pick. ngrok.com/blog/ai-gate...
ngrok.com
AI Gateway: use Anthropic and OpenAI with one API key | ngrok blog
Create an AI Gateway API Key, add credits, and start making requests to OpenAI and Anthropic—ngrok handles the rest.
021
ngrok @ngrok.com · 19/02/2026
ngrok's AI gateway now supports the Anthropic SDK natively. Change your base_url, keep your prompt caching, extended thinking, all of it. The diff is one line & there's no step two. ngrok.com/blog/native-...
021
Reposted by ngrok
Sam Rose @samwho.dev · 19/02/2026
What do LLMs see? I wrote a lil' tool that extracts the attention matrices out of open models and creates this typing visual, with each token's opacity changing according to its average attention score as the prompt progresses. Dimmer words are considered less important to the model.
1726444
Reposted by ngrok
Overcommitted Podcast @overcommitted.dev · 10/02/2026
This week on Overcommitted, we got to sit down with Bluesky's favorite tech blogger @samwho.dev and it did not disappoint! Sam makes some of the coolest tech content on the internet, and if you haven't heard from him yet, you should! Full episode out now: overcommitted.dev/interactive-...
0215