Koyeb
LightNews LightNews
koyeb.com
Koyeb
@koyeb.com
28 followers 1 following 42 posts
Koyeb provides the fastest way to deploy intensive apps globally with a developer-friendly serverless platform. No ops, servers, or infrastructure management.
Posts Replies Media Videos
koyeb.com
Changelog 103 is live! Here's what's new at Koyeb:

✅ Improved volume management in the control panel
🚀 Streamlined one-click apps catalog now GA
⚙️ @tenstorrent SSH access and new model deployment
🧑‍💻 New tutorial: Fine-tune a Whisper TTS model w/ @UnslothAI

Learn more 🧵👇
November 12, 2025 at 2:57 PM
koyeb.com
Looking for the best way to deploy your remote MCP servers? Look no further 👇

Start running your MCP server on Koyeb and benefit from native Scale-to-Zero and autoscaling from the get-go 🚀
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
November 12, 2025 at 11:03 AM
koyeb.com
Inspired by tools like v0, Create, Replit, and Same, app.build is the open source AI agent that builds and deploy full-stack web apps straight from your terminal from the engineers at @neondatabase

youtu.be/n58L5n9Gk_k...
app.build: Generate & Deploy Full-Stack Apps with an Open-Source AI Agent
See how app.build, an open-source AI agent by Neon, generates and deploys full-stack web apps from a single prompt.
www.youtube.com
November 11, 2025 at 4:04 PM
koyeb.com
Deploy @OpenAI gpt-oss-20b with @sgl_project on Koyeb GPU for high-performance, low-latency, and efficient inference in one-click 👇
www.koyeb.com/deploy/gpt-...
Deploy gpt-oss-20b One-Click App - Koyeb
Deploy OpenAI gpt-oss-20b with SGLang on Koyeb GPU for high-performance, low-latency, and efficient inference.
www.koyeb.com
November 11, 2025 at 11:00 AM
koyeb.com
Deploy @Alibaba_Qwen Next 80B A3B Instruct with vLLM on Koyeb GPU for high-performance, low-latency, and efficient inference in one-click 👇
www.koyeb.com/deploy/qwen...
Deploy Qwen 3 Next 80B A3B Instruct One-Click App - Koyeb
Deploy Qwen Next 80B A3B Instruct with vLLM on Koyeb GPU for high-performance, low-latency, and efficient inference.
www.koyeb.com
November 10, 2025 at 4:00 PM
koyeb.com
What if your AI could literally speak with a new voice?

With @UnslothAI, it's possible to take an existing TTS model and train it on a curated dataset to recreate a specific speaking style! 🗣️

Check out our tutorial to learn how to get started 👇
November 10, 2025 at 2:06 PM
koyeb.com
Looking for an easy way to stay updated with the latest news? 📰

Discover how to build an app that sends you the latest @hackernews stories through @WhatsApp using @OpenAI's gpt-oss-20b, Supersonic and @twilio 🧑‍💻
November 10, 2025 at 1:07 PM
koyeb.com
You know @anyshiftio as the AI SRE for your infrastructure 🤖 🚀

Discover how Anyshift scales real-time queries across millions of nodes with Koyeb 👇
www.koyeb.com/blog/how-an...
How Anyshift Scales Real-Time Queries Across Millions of Nodes with Koyeb - Koyeb
Discover how Anyshift, an AI-powered infrastructure assistant, leverages Koyeb’s serverless platform to scale, prototype faster, and manage high-performance infrastructure with ease.
www.koyeb.com
October 27, 2025 at 3:26 PM
koyeb.com
Want your LLM to interact w/ your database? This tutorial covers how to use @Gradio to build MCP servers that:
🐘 Connect to a @PostgreSQL database
🔎 Let clients discover schema & tables
❓ Run queries

Then, deploy it on Koyeb and enjoy built-in autoscaling & scale-to-zero 🚀
October 25, 2025 at 9:19 AM
koyeb.com
Did you miss the Main Stage talks at @aiDotEngineer Paris?

Rewatch the livestream to catch talks from:
🎦 @andi_blatt - @bfl_ml
🎬 @yann_eu - @gokoyeb
📽️ @aparnadhinak - @arizeai
🍿 @reach_vb - @huggingface
🎥 @DynamicWebPaige - @GoogleDeepMind
👀 @steeve - @zml_ai

& more! www.youtube.com/watch?v=wyU...
AI Engineer Paris 2025 (Day 2)
Full schedule at https://www.ai.engineer/paris#schedule- Emil Eifrem, Co-Founder and CEO, Neo4j, “The State of^H^Hin AI Engineering”- Tushar Jain, President,...
www.youtube.com
October 24, 2025 at 1:25 PM
koyeb.com
Did you know you can expose TCP ports of your Koyeb services publicly? With TCP Proxy, you can make any TCP service publicly accessible! Perfect for running:

- Databases like @MySQL @MongoDB @Redisinc
- Remote access protocols like SSH, RDP & VNC
- IoT protocols like MQTT & AMQP
October 23, 2025 at 7:06 AM
koyeb.com
Looking for an easy way to finetune and train LLMs faster?

🦥 Check out @UnslothAI to train, run, and evaluate LLMs 2x faster with 70% less RAM ❤️‍🔥 www.koyeb.com/deploy/unsloth
Deploy Unsloth One-Click App - Koyeb
Unsloth lets you easily finetune & train LLMs faster.s
www.koyeb.com
October 22, 2025 at 1:21 PM
koyeb.com
Cache us if you can! 👀 Want to hear the story of how we chased a latency spike across our globally distributed stack?

☕️ Grab a coffee and join us for an engineering investigation into @EnvoyProxy, @HashiCorp's Consul and some surprising caching behavior www.koyeb.com/blog/from-e...
From Envoy to Consul: Chasing a Latency Spike Across a Globally Distributed Stack - Koyeb
The story about how a latency issue led us to investigate across the stack — from Envoy to Consul’s caching behavior.
www.koyeb.com
October 21, 2025 at 2:02 PM
koyeb.com
Looking for a fun weekend project? 🧑‍💻

Learn how to build a text-to-speech app using Dia 1.6B, @FastAPI, and @sveltejs 🔥
www.youtube.com/watch?v=mVQ...
Using Dia 1.6B to Build a Text-to-Speech App on Serverless GPUs
Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.
www.youtube.com
October 18, 2025 at 11:15 AM
koyeb.com
Scale-to-Zero is fantastic for reducing idle costs 💥
What's the best way to avoid cold starts? Light Sleep! ⚡️

See how quickly services wake up with Light Sleep 👇
October 17, 2025 at 11:43 AM
koyeb.com
Deploy Qwen 3 VL 235B A22B Instruct with vLLM on Koyeb GPU for high-performance, low-latency, and efficient inference in one-click👇
www.koyeb.com/deploy/qwen...
Deploy Qwen 3 VL 235B A22B Instruct One-Click App - Koyeb
Deploy Qwen 3 VL 235B A22B Instruct with vLLM on Koyeb GPU for high-performance, low-latency, and efficient inference.
www.koyeb.com
October 16, 2025 at 1:03 PM
koyeb.com
What if your AI could decide when it needs backup? 🤔

Our new tutorial shows how a local @huggingface SmolLM2 model offloads tough programming questions to @Alibaba_Qwen 3 Next 80B served on Koyeb with @vllm_project 💥
October 15, 2025 at 1:02 PM
koyeb.com
👋 Good morning @AllThingsOpen!

Catch @yann_eu and Greg Wallace from @netactuate share and demo how we deployed @tenstorrent Wormhole and Blackhole technology into the cloud at 11:30 AM ☁️

Who wants to take these instances for a test drive? 🏎️ 🏁
October 14, 2025 at 1:02 PM
koyeb.com
Who's in Raleigh for @AllThingsOpen? 👋

We'll be there with our friends from @netactuate to talk about how we deployed next-generation AI accelerators from @tenstorrent into the cloud 🚀
October 13, 2025 at 12:14 PM
koyeb.com
Curious about the engineering behind 200ms cold starts on the platform?

Dive into the internals of Light Sleep Scale-to-Zero with our post written by the engineers that built it 👇 www.koyeb.com/blog/scale-...
Scale-to-Zero: Wake VMs in 200ms with Light Sleep, eBPF, and Snapshots - Koyeb
Discover how we built Scale-to-Zero to automatically wake VMs in 200ms with eBPF, light sleep, and snapshots.
www.koyeb.com
October 10, 2025 at 1:25 PM
koyeb.com
Cache us if you can! 👀 Want to hear the story of how we chased a latency spike across our globally distributed stack?

☕️ Grab a coffee and join us for an engineering investigation into @EnvoyProxy, @HashiCorp's Consul and some surprising caching behavior www.koyeb.com/blog/from-e...
From Envoy to Consul: Chasing a Latency Spike Across a Globally Distributed Stack - Koyeb
The story about how a latency issue led us to investigate across the stack — from Envoy to Consul’s caching behavior.
www.koyeb.com
October 10, 2025 at 1:22 PM
koyeb.com
Want to interact with your Koyeb resources using natural language?

The Koyeb MCP Server lets you:
🔹 Create and deploy applications
🔸 Update services
🔹 Execute commands on instances
🔸 Retrieve information, logs & metrics from your services

Learn how to get started 👇
www.koyeb.com/blog/koyeb-...
Koyeb MCP Server: Interact with your Koyeb Resources in Natural Language - Koyeb
Today we're announcing the Koyeb MCP Server in public beta to let you interact with your Koyeb resources in natural language.
www.koyeb.com
October 9, 2025 at 10:54 AM
koyeb.com
Did you see our latest changelog? 🔥👇

📃 Scale-to-Zero events & wake up time in logs
👷 Builder selection during Service creation for git-based deployments
📧 Turn off deployment failure notifications
🚀 New One-Click Deploys: @Alibaba_Qwen 3 VL 235B A22B Instruct & @UnslothAI
October 6, 2025 at 2:41 PM
Reposted by Koyeb
thibaultleouay.dev
Being multi-cloud opens up so much for @openstatus.dev

We can use our @fly.io probes to monitor our @gokoyeb.bsky.social probes 🔥

And our @gokoyeb.bsky.social probes to monitor our @fly.io probes 🚀
October 4, 2025 at 3:24 PM
Reposted by Koyeb
cle-does-things.bsky.social
I'm determined to play around more with building web apps with @golang.org, and I've been searching for a deployment option.
I came across @gokoyeb.bsky.social: very nice DevX, deployed in less than a minute with @docker.com, integrated CD with @github.com, all from their dashboard.
Kudos!
September 19, 2025 at 7:45 PM