Autonomous Cloud for Serverless and AI Infra. Leaping Beyond K8s
For the last 3 years, I have been working on a way to solve inefficiencies in software infrastructure. Introducing Taubyte. What is Taubyte? Taubyte is an open-source, autonomous cloud platform focusing on serverless and AI infrastructure. Designed to be edge-native and GitOps-centric, Taubyte aims to democratize cloud computing and reduce ops overhead. Why Choose Taubyte? The Future is Autonomous! - Ready-to-Go Platform: Unlike Kubernetes, which often requires additional products, Taubyte delivers a fully-functional cloud network out-of-the-box. - Low to No Ops: Taubyte's autonomous nature…
What it does
In the maker’s words, at launch
For the last 3 years, I have been working on a way to solve inefficiencies in software infrastructure. Introducing Taubyte. What is Taubyte? Taubyte is an open-source, autonomous cloud platform focusing on serverless and AI infrastructure. Designed to be edge-native and GitOps-centric, Taubyte aims to democratize cloud computing and reduce ops overhead. Why Choose Taubyte? The Future is Autonomous! - Ready-to-Go Platform: Unlike Kubernetes, which often requires additional products, Taubyte delivers a fully-functional cloud network out-of-the-box. - Low to No Ops: Taubyte's autonomous nature eliminates the need for constant operational maintenance. Taubyte's self-governing system literally runs itself! - Horizontal Scaling: Built-in support for horizontal scaling, no additional configurations needed. - Serverless Focus: While Kubernetes can support serverless via add-ons, Taubyte is natively designed for serverless computing. Repos and Tools: - Tau (github.com/taubyte/tau): Deploy on servers to form a Cloud Network—a connected ensemble of Taubyte nodes identified by an FQDN. - Dreamland (github.com/taubyte/dreamland): Use on your PC/laptop for E2E testing and local cloud simulation. - Tau-CLI (github.com/taubyte/tau-cli): GitOps-centric CLI for managing projects across different Cloud Networks. - VM-Orbit (github.com/taubyte/vm-orbit): Extend WebAssembly VM capabilities for serverless function calls. Dive Into Our Showcases & Resources: - 8bit.ws: The cloud, but cooler. An AI playground built on Taubyte featuring serverless LLM via llama-cpp and NVIDIA, supercharged by VM-Orbit. Check Out the Plugin Source Code. - Sandbox: Experiment on sandbox.taubyte.com via tau-cli or console.taubyte.com. - Documentation: Comprehensive guides available at tau.how. Get Involved: - Test It: Use Dreamland for local tests or sandbox.taubyte.com for a live experience. - Join the Revolution: PRs, issues, and your genius are all welcome.
Does the same job
all alternatives →
- HAHasura – A Postgres BaaS and Kubernetes PaaS on Your Own Infrastructure2017 · hasura.io · ▲259
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
