Vibe Computing: AI-Powered Multi-Cloud Orchestration With Cloud-Barista
summary
Cloud-Barista is an Apache‑2.0 Go platform that unifies heterogeneous cloud APIs via CB‑Spider and CB‑Tumble and adds an MCP server to map natural‑language intent to infrastructure actions. It already supports 10 clouds and discovery across 180 regions, catalogs ~100,000 specs including ~7,000 GPU SKUs and ~400,000 images, and runs from a Docker Compose stack. Demos provision eight GPU VMs with automatic CUDA driver install and model distribution, and an MCP agent (VS Code/Copilot or Claude) creates 14–15 VMs, deploys localized sites and a roulette game with retries that succeed.
AI-written summary · about
chapters (7)
- 0:00Vibe Computing & Cloud-Barista
- 4:31Cloud-Barista multicloud
- 11:40Why Cloud-Barista created
- 21:06Demo AI services deploy
- 27:46Global game service deploy
- 30:23MCP integration for AI
- 36:26Closing & future plans
related talks
33mUnleash the Multi-Cloud with BOSH
16mSky Computing: Charting a New Course in AI Cloud Infrastructure
27mFrom Supercomputing to Serving: A Case Study Delivering Cloud Native Foundation Models
16mA novel Cloud High Performance Computing infrastructure for user
34mOpen Source AI Agents on User-Owned Infra: K3s, MCP, & GPU Sharing in Practice
16mBOSH & GPU - a Match Made in Heaven
36mQuantum & High-Performance Computing in The Cloud
06mAutoscaling GPU Clusters Anywhere — Hyperscalers, Neoclouds & Ba...