Vibeos — AI skill for Claude Code
AI-native Linux: Ubuntu 24.04 LTS, KDE Plasma, a local Ollama model and an agent CLI, installed in about 10 minutes.
How to install Vibeos
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Matswm86/vibeos and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Vibeos does
AI-native Linux: Ubuntu 24.04 LTS, KDE Plasma, a local Ollama model and an agent CLI, installed in about 10 minutes. You choose the model and the provider: swap the local model, bring your own hosted key, or stay fully offline. Claude Code is the shipped default, not a requirement.
Alternatives in AI
- Opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama… 12.3k ★
- Chat Ollama — ChatOllama is an open source agentic app for running AI agents across local and hosted models 3.5k ★
- Firm — Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preser 1.3k ★
README
VibeOS
**AI-native development environment for Linux. Free. Open source. Fun.**

*Vibbey, the VibeOS onboarding assistant, in the Neon Grid UI. Groq primary + local Ollama fallback, real 3D Clippy-lineage model, zero telemetry.*
VibeOS turns a fresh Linux machine into a fully configured Claude Code workspace — with local AI models, persistent memory, tool-aware onboarding, and just the MCP servers you actually need. **Vibbey**, your nostalgic desktop assistant, lives in the bottom-right corner of your screen and walks you through setup.
**Which branch?** `main` is the v1 line (Kubuntu 22.04 base), frozen at tag `v1.0.4.3-final`. The Ubuntu 24.04 rebuild (v2, built with mkosi) is developed on the [`v2` branch](https://github.com/Matswm86/vibeos/tree/v2); its latest tag is `v2.0.0-rc1`.
Choose your path
🐧 Path A — "I already have Linux"
One command on your existing Ubuntu 22.04+ (including Kubuntu), Pop!\_OS 22.04+, or Debian 12+ install:
curl -sSL https://raw.githubusercontent.com/Matswm86/vibeos/main/install.sh | bash
Takes ~10 minutes (apt + npm + Ollama model pull). After it finishes, Vibbey pops up as a floating desktop widget and walks you through first-boot setup. Vibbey runs on Groq cloud (smart, fast) with local Ollama fallback (private, offline) and greets you with:
*"Looks like you're about to Vibe hard. Would you like to continue? ;)"*
**Status**: shipped, v0.4.1. Stable.
💿 Path B — "Start from scratch"
**The v0.4.1 ISO (4.7 GB) has no working download link right now.** It was published at `iso.mwmai.no`, which was taken offline on 2026-06-11. Build the ISO from this repo instead (see [Path B (ISO build): test locally](#path-b-iso-build--test-locally)). The SHA-256 of the released ISO is recorded in [`deploy/iso-landing/SHA256SUMS`](deploy/iso-landing/SHA256SUMS).
Flash the ISO to a USB with [balenaEtcher](https://www.balena.io/etcher/), boot your machin
Related Skills
JustDay
Your own JARVIS for Linux: a voice-and-keyboard AI agent for KDE Plasma 6 that does things — apps, windows, mu
KodexBar Suite
Linux AI quota monitor and KDE Plasma 6 widget for Claude Code, OpenAI Codex, Cursor, Grok, OpenCode Go, and A
Plasma AI Usage Monitor
KDE Plasma 6 widget for local AI provider usage, spend, limits, and coding-tool activity
Kintsugi Usb
AI-assisted rescue boot USB — a Ventoy multi-boot drive on Ubuntu 24.04 with offline LLM inference (Ollama + l
Wingman
Multi-provider terminal coding agent in Rust — bring your own model (Anthropic, OpenAI, Gemini, Ollama, OpenRo
ReqSolve
Self-hosted, AI-assisted ticketing & request management for organizations — multi-department with strict isola
Related Agents
Byok Token Security Expert
BYOK (Bring-Your-Own-Key) and OAuth token security expert. Deep on cross-platform OS keychain integration (mac
ZeroClaw Android
Run AI agents 24/7 on your Android phone. Native Rust core, 25+ providers (OpenAI, Claude, Gemini, Groq, DeepS
Bench Runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scrip