KubeCon Cochair/Keynote, KCD organizer, CNCF ambassador, founding member @realwasmedge; @Olares_OS: K8s-based, secure local execution environment for AI agents
Austin, TX
Joined October 2012
- Tweets2K
- Following632
- Followers524
- Likes4.9K
MortyC137 retweeted
Bring Hermes Agent into your SSH workflow.
With Hermes on Olares, you can let it work on a connected machine within the permissions you configure.
Read the guide 👇
olares.com/docs/use-cases/he…
MortyC137 retweeted
终于官宣了，KCD Beijing 明年 3 月继续 😁
欢迎大家一起来玩！
Kubernetes Community Days are kicking off for H1 2027! 📍
These community-organized events bring open source practitioners together for local technical learning and networking.
We also updated our structure so first-time KCDs are now Tier 0 and Tier 2 events are Independent to better support organizers as they scale.
Check out the full H1 lineup on the blog: bit.ly/4x4xr7U
MortyC137 retweeted
Appreciate the spot-on recommendation!
¡Muchas gracias!😄
¿Y si tu propia computadora pudiera convertirse en una nube personal y servidor de IA?
Olares es un sistema operativo gratuito y open source pensado para transformar tu hardware en una infraestructura personal. Permite almacenar y gestionar tus datos, alojar aplicaciones, ejecutar modelos de IA y acceder a tus servicios desde cualquier lugar.
Una propuesta interesante para quienes quieren reducir la dependencia de las grandes nubes y tener su propia infraestructura en casa.
nosubscription.org/software/…
MortyC137 retweeted
We’re heading to IFA 2026—and we want our community there with us.
We’re giving away 8x IFA 2026 2-DAY-TRADE-VISITOR-TICKETS (worth €99 each)!🎟️
How to enter:
1️⃣ Follow @Olares_OS
2️⃣ Like this post
3️⃣ Reply: Tell us what kind of Olares One demos you’d love to see live in Berlin.
Schedule & details below 👇
#IFA2026 #OlaresAtIFA
MortyC137 retweeted
Qwen 3.8-27b is out now on #Olares Market. 🫡
olares.com/market/app/market…
We promised open weights for Qwen3.8. Now, time to meet them! 🎉
⚡ Qwen3.8-27B:
- A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world coding & office workflows.
- 262K native context, easily extendable to 1M tokens via YaRN.
- Built for builders. Highly efficient, high-quality, and licensed under Apache 2.0.
🚀 The open weights for Qwen3.8-2.4T-A95B (Max-level) have also been released recently.
Whether you're shipping lightweight applications with Qwen3.8-27B locally or building agents with Qwen3.8-2.4T-A95B, they're yours now!
Download, deploy, and build something we haven't imagined yet. 👀👇
- Hugging Face：
huggingface.co/collections/Q…
- ModelScope：
modelscope.cn/collections/Qw…
MortyC137 retweeted
#MiniMax H3 brings stunning cinematic video generation, and the new ComfyUI v0.3.0 is already live on Olares to support it!
We’ve already tested it on Olares One to ensure smooth performance.
Update #ComfyUI on #Olares to take it for a spin: olares.com/market/app/market…
MortyC137 retweeted
Olares is heading to Open Source Summit Korea! 🇰🇷(@linuxfoundation)
Real open-source AI is more than just chat interfaces. We built a #Kubernetes-based operating system to run AI workloads directly on user-owned infra.
CNCF Ambassador @MileyFu will use Olares as a case study to show how to make local AI practical for everyday developers.
Bookmark the session so you do not miss it! 👇
#OSSummit #OpenSource
osskorea2026.sched.com/event…
MortyC137 retweeted
This is great I have had my olares a couple months now and it proving to be a great asset to my business
MortyC137 retweeted
Europe’s AI rules are entering a new phase as the EU AI Act’s transparency obligations take effect.
Against this backdrop, Olares One is making its European debut at @IFA_Berlin.
Discover what’s next for personal AI cloud in Berlin, September 4–8. 🇩🇪
#IFA2026 #Olares #LocalAI
olares.com/blog/meet-olares-…
MortyC137 retweeted
Running local AI and self-hosted apps shouldn’t mean stitching together every infrastructure layer yourself.
Olares is a self-hosted personal cloud operating system for builders who want to manage data, apps, and AI workloads on their own hardware.
It helps you create an all-in-one self-hosted environment by combining application services with storage, networking, databases, GPU infrastructure, and Kubernetes-based components.
Key features:
• Local AI stack – host models, manage GPUs, and build private knowledge bases.
• App isolation – sandboxing separates applications and permissions.
• Unified data layer – file system and database services include automated scaling and backups.
• Single sign-on – one shared authentication service covers installed applications.
• Anywhere access – mobile, desktop, and browser clients connect to your devices.
Free public GitHub repo. Its root LICENSE is AGPL-3.0, while LICENSE.md contains separate Olares terms limiting commercial use and redistribution.
Link in the reply 👇
MortyC137 retweeted
🎉 We hit #1 on GitHub Trending!
If you are new here, #Olares is an open-source personal cloud operating system designed to run local AI models and manage data securely on your own hardware.
Thank you to everyone who has supported our vision for private AI infrastructure.
Discover what we are building:
github.com/beclab/Olares
MortyC137 retweeted
We are excited to share that NVIDIA NemoClaw now runs on Olares OS!
You can now run your entire AI agent stack locally and securely on devices ranging from the Olares One desktop to NVIDIA DGX Spark systems. @NVIDIA_AI_PC
Learn more:
blog.olares.com/olares-os-no…
MortyC137 retweeted
#OpenCode is an open-source AI agent that seamlessly writes code in your terminal, IDE, or desktop. It supports 75+ LLMs, multi-session workflows, and native GitHub Copilot or ChatGPT Plus integrations.
The latest update on #Olares further expands these capabilities, introducing a brand-new Terminal entrance with an auto-start TUI and the built-in oh-my-openagent (OMO) plugin.
Head over to Olares to give it a try.
market.olares.com/app/market…
MortyC137 retweeted
Caio Delgado is back with a new #Olares One review!
In the video he generates video with WAN 2.2 in ComfyUI, runs #Gemma4 and Qwen 3.5 locally, puts an #OpenClaw agent on Telegram, and streams Cyberpunk 2077 to his Steam Deck, all from one machine with an RTX 5090 Mobile inside.
The GPU allocation modes in Olares OS are what make it possible to do all of that without the card getting in its own way. And thanks to the vapor chamber cooling, the chassis stays at 28°C under load.
Full review: 👇
youtube.com/watch?v=lQDwKHC8…
MortyC137 retweeted
DGX Spark owners rejoice! Olares OS is now available on @NVIDIA_AI_PC ’s DGX Spark! It comes with a sophisticated sandbox system + an App Store for containerized AI apps, that fully utilize your GPUs. Run multiple AI agents & local models securely & efficiently on your Spark!
MortyC137 retweeted
GOSIM Paris 2026 lucky draw is live!
We're handing out discount codes for this year's conference (May 5–6 at STATION F) — and some of them are pretty significant.
The speaker lineup this year is stacked — NVIDIA, Google, Moonshot (Kimi), MiniMax, GLM, and others working at the frontier of open-source AI and LLMs. Check out paris2026.gosim.org for the full picture.
How to enter:
- Follow our page
- Repost this
- Tag a friend who you'd like to join at GOSIM
We'll DM winners with their codes. That's the whole thing.
MortyC137 retweeted
You bought a $4,000 computer with a powerful GPU. Your goal is to set up Agent Harness that can learn from you and get better at YOUR tasks over time. That harness includes local AI models, cloud APIs, data collection, knowledge mgmt, RL infra (eg. autoresearch), finetuning tools & skills / CLI tools. But there is one problem:
The AI agents are fundamentally non-deterministic and must be sandboxed. But existing sandbox solutions lack ready-to-use agent harness, especially for GPU workloads.
I am thrilled that the open source @Olares_OS released support for DGX Spark today! It features a container system that fully utilizes the GPU. It comes with many applications, agents, and harness pre-configured and can be installed with one-click.
Try it on your Spark today: blog.olares.com/olares-relea…
The open source repo: github.com/beclab/Olares
