Koyeb
koyeb.com
Koyeb
@koyeb.com
Koyeb provides the fastest way to deploy intensive apps globally with a developer-friendly serverless platform. No ops, servers, or infrastructure management.
πŸš€ Build your AI stack in minutes, not weeks.

With Koyeb One-Click Models & AI Apps, deploy production-ready AI on high-performance serverless infrastructure in the the click of a button.

⚑ No infra management
⚑ No setup
⚑ Just ship

πŸ‘‰ app.koyeb.com/one-clicks
January 16, 2026 at 8:41 AM
πŸš€ Want to deploy remote MCP servers without managing your own infrastructure?

With Koyeb, you can spin up high-performance, fully serverless MCP servers in seconds.

Scalable, pay-as-you-go, and globally distributed πŸŒπŸ’¨
www.koyeb.com/tutorials/d...
Deploy Remote MCP Servers to Koyeb using Streamable HTTP Transport - Koyeb
Learn how to build and deploy Remote Model Context Protocol (MCP) servers to Koyeb using Streamable HTTP transport.
www.koyeb.com
January 15, 2026 at 8:29 AM
βœ… Save resources when they're not in use, and get up and running quickly as soon as they are needed.

You can get started today with Light Sleep and leverage the benefits of high-performance serverless infrastructure ❀️‍πŸ”₯
www.koyeb.com/blog/avoid-...
Avoid Cold Starts With Scale-to-Zero Light Sleep - Koyeb
We're thrilled to announce the public preview of Light Sleep: a Scale-to-Zero enhancement leveraging memory snapshots to instantly wake up MicroVMs.
www.koyeb.com
January 12, 2026 at 2:52 PM
⚑️ Light Sleep allows you to enable Scale-to-Zero with no noticeable latency impact for end-users, enabling users operating large container fleets to dramatically improve efficiency with zero performance compromise.

Check out how fast cold starts are with light sleep enabled πŸ‘‡
January 12, 2026 at 2:52 PM
Apply today to build the serverless future of tomorrow πŸš€πŸ‘‡ www.koyeb.com/careers
Koyeb: High-performance Infrastructure for APIs, Inference, and Databases
Deploy intensive applications across GPUs, CPUs, and Accelerators in minutes - scale in 50+ locations.
www.koyeb.com
January 10, 2026 at 11:31 AM
πŸ†• Ready to build the future of AI & cloud? Join us πŸ™Œ

We're hiring:
πŸ”Έ Software Engineers
πŸ”Έ Senior Fullstack Engineer
πŸ”Έ Senior Frontend Engineer
πŸ”Έ Founding Sales/ CS

Know someone who'd like one of these roles? Do us both a solid and tag them below! 🌐 πŸš€
January 10, 2026 at 11:31 AM
πŸ‘‹ Hey AI developers in Paris! ​We're kicking 2026 off with the first AI Developer Meetup of the New Year! πŸ’«

Join us for an evening of talks and demos from leading AI engineers for developers eager to learn more and build with AI.

RSVP: luma.com/elif78ks
AI Developer Meetup on Coding Agents Β· Luma
We're kicking 2026 off with the first AI Developer Meetup of the New Year! Join us for an evening of talks and demos from leading AI engineers for developers…
luma.com
January 9, 2026 at 2:45 PM
Want to learn more about GPU benchmarking? Watch the full video over on our Youtube channel!
youtu.be/j0UuDNR9fU0
Choosing a GPU for your LLM - What to consider when benchmarking
We ran GPU benchmarks on 3 different LLMs deployed on Koyeb β†’ https://shorturl.at/cFkyWIn this video, we cover what values we measured in our benchmark, why ...
www.youtube.com
January 8, 2026 at 8:04 PM
Dive into the world of GPU benchmarking! Picking the perfect GPU for deploying your model can be tricky. πŸ§‘β€πŸ’»

Don't just focus on RAM. Identify the key metrics you should measure for based on your model's production use. βœ…

Tune in to Part 1 and discover insights on measuring by batch size! πŸ‘‡
January 8, 2026 at 8:04 PM
Want to integrate custom tools into ChatGPT? Use @OpenAI's SDK to create apps right inside ChatGPT.

Check out our tutorial on building ChatGPT tools with OpenAI SDK and Koyeb: www.koyeb.com/tutorials/b...
Use OpenAI Apps SDK in ChatGPT with MCP deployed on Koyeb - Koyeb
Learn how create an app for the OpenAI Apps SDK with Node.Js and serve it from Koyeb
www.koyeb.com
January 7, 2026 at 2:17 PM
Check out the Youtube short and readme to get started! ❀️‍πŸ”₯
www.youtube.com/shorts/ZnmN...
I built a New Year’s bingo board-generating app #aidevelopment #javascript #reactjs #llm
I created an app that generates bingo cards to track small wins over 2026. You can generate the squares using a prompt, edit squares as you choose, and downl...
www.youtube.com
January 5, 2026 at 4:44 PM
What's on your 2026 bingo card? Build your own with @reactjs, a @nestframework backend, and an LLM!

πŸ€– Let an agent design tasks tailored to your goals
πŸ“ Customize your bingo squares as you'd like
πŸš€ Run locally or deploy effortlessly with Koyeb
January 5, 2026 at 4:44 PM
πŸŒ‰ Happy New Year to everyone in the same time zone as our SF location!

Cheers to a year of building, deploying, scaling AI with ease this New Year! πŸ₯‚ πŸš€
January 1, 2026 at 8:00 AM
Cheers to everyone ringing in the New Year with us in the Washington, D.C. time zone! πŸ₯³

Gear up for a year of lightning-fast, hassle-free AI deployments across the globe, wherever you need them! 🌐
January 1, 2026 at 5:00 AM
Happy New Year to everyone celebrating in the same time zone as our Frankfurt and Paris core locations! πŸ‡ͺπŸ‡Ί

πŸ₯‚ Frohes neues Jahr!
πŸ’« Bonne annΓ©e !
πŸŽ† Buon anno!
πŸ₯³ SzczΔ™Ε›liwego Nowego Roku!

Wishing everyone the best and fastest AI deployments this year!
December 31, 2025 at 11:00 PM
Codex, developed by @OpenAI, helps you write features, answer questions about your codebase, squash bugs, and review PRs.

Learn how to use a Koyeb Sandbox to securely run its dynamically generated code πŸ§‘β€πŸ’» www.youtube.com/watch?v=TJ3...
December 27, 2025 at 10:02 AM
Looking to deploy SOTA models on high-performance infrastructure in one-click? πŸš€

Get up and running with the best models from @MistralAI, @bfl_ml, @GoogleDeepMind, and more.

Head on over to app.koyeb.com/one-clicks
December 25, 2025 at 2:04 PM
Watch Discovery Track talks from AI Engineer Paris now: youtube.com/playlist?li...
Discovery Track 1 - AI Engineer Paris 2025
www.youtube.com
December 24, 2025 at 11:02 AM
One of the highlights of @aiDotEngineer Paris was the depth of the conversations on the Discovery Tracks:
πŸ”Έ MCP isn’t good yet: We got to 30M requests/ month - @Sentry
πŸ”ΈΒ Rewriting all of Spotify’s code base, all the time - @Spotify
πŸ”ΈΒ LLM-Based GUI Agents - @BMW

And more!
December 24, 2025 at 11:02 AM
🍡 The holidays are a great time to slow down and catch up on the ideas that matter.

If you missed it, our @aiDotEngineer Paris Main Stage talks are now available as a playlist on YouTube 🎞️

Watch now πŸ‘‡
youtube.com/playlist?li...
December 23, 2025 at 12:11 AM
πŸ” Our new authentication system brings features like 2FA, MFA and passkeys, keeping your login experience smooth and secure

Check them out and get started πŸ‘‡
December 22, 2025 at 1:47 PM
Learn how to use the Claude Agent SDK with Koyeb Sandboxes πŸ‘‡
www.koyeb.com/tutorials/u...
Using the Claude Agent SDK with Koyeb Sandboxes for Secure Code Execution - Koyeb
Learn how to build AI agents that execute code safely and autonomously using the Claude Agent SDK and Koyeb Sandboxes for secure, isolated code execution.
www.koyeb.com
December 20, 2025 at 1:02 PM
Safely develop autonomous AI agents! With the @claudeai Agent SDK from @anthropic and Koyeb Sandboxes, your agents can handle tasks like file creation and command execution without endangering your infrastructure.
December 20, 2025 at 1:02 PM
Watch here to learn about benchmarks and choosing the right GPU for your workload πŸ‘‡
www.youtube.com/watch?v=j0U...
Choosing a GPU for your LLM - What to consider when benchmarking
We ran GPU benchmarks on 3 different LLMs deployed on Koyeb β†’ https://shorturl.at/cFkyWIn this video, we cover what values we measured in our benchmark, why ...
www.youtube.com
December 19, 2025 at 8:51 AM
πŸŽ₯ New video: What to consider when benchmarking and choosing a GPU for your LLM

We discuss 5 key metrics to benchmark: batch size, token counts, throughput, average latency, and wall-clock time ⏱️ and help you identify which ones you should care about the most
December 19, 2025 at 8:51 AM