Waifu stack
dev cli/tui only - no 3d creating
日々が過ぎゆく中で、ターミナルで幸せに生きよう。
❃ cpu : ryzen
❃ os : nixos
❃ wm : niri
❃ taskbar : quickshell
❃ term : ghostty
❃ shell : nushell
❃ font : JetBrainsMono Nerd
nix docs is kinda hard ; arch wiki rocks
Waifu stack
dev cli/tui only - no 3d creating
日々が過ぎゆく中で、ターミナルで幸せに生きよう。
❃ cpu : ryzen
❃ os : nixos
❃ wm : niri
❃ taskbar : quickshell
❃ term : ghostty
❃ shell : nushell
❃ font : JetBrainsMono Nerd
nix docs is kinda hard ; arch wiki rocks
Wayland Niri X Quickshell = Custom taskbar for *nix
Type : TUI
Environment : Local
Isolation workspace : No
Isolation runtime : Apple Virtualization.framework
Local-First Sandboxes for AI Agents on macOS.
Lightweight Linux VMs powered by Apple Virtualization.framework.
Ephemeral by default. No Docker required.
No emulation layer
Near-native speed on ARM64.
Type : TUI
Environment : Local
Isolation workspace : Git worktree
Isolation runtime : No
Run Claude, Codex, and Gemini CLIs side-by-side with built-in Git integration. Easily switch agents and manage up to 10 concurrent sessions via tabs.
Features include real-time streaming, token tracking, and full session persistence to resume work with context intact.
Type : CLI
Environment : Cloud
Isolation workspace : no
Isolation runtime : Firecracker
Launch secure E2B Sandboxes in just 80ms. Built specifically for AI agents, they provide a full suite of tools for any workflow.
Powered by Firecracker microVMs, each sandbox ensures robust isolation for safely running untrusted code.
Esprit AI deploys autonomous hacker agents that scan your code, find vulnerabilities, validate exploits, and generate fixes — 10x faster than manual pentesting.
Native macOS app built on Ghostty. Vertical tabs, notification rings when agents need attention, split panes, and a socket API for automation.
cmux.dev
Claude
grep -ohP "useEffect(.?[\K[^]+" **/.tsx 2>&1|tr ',' '\n'|awk 'NF{$1=$1;a[$0]++}END{for(k in a)print a[k],k}'| sort -rn| head -20
👀 yea.. go
It started in 2007 (CUDA)
Transformers, the architecture behind ChatGPT, require billions of mathematical computations, giant matrix multiplying each other at lightning speed that must be performed simultaneously in parallel, particularly for the attention mechanism.
CUDA is the software layer that unlocks Nvidia GPUs to execute these billions of operations simultaneously
perfect fit for Mistral AI’s sandboxes
🐁
NixOS X AGS
A framework for crafting Wayland Desktop Shells
Openclaw
Browser automation is hard
One advantage of having a Mac Mini or an x86 mini PC at home is that you benefit from a residential IP address, whereas 50% of VPS IP addresses will be blocked by websites, which is very useful for web automation.
Deployment Options Compared
Austria Vibe
Openclaw
🇦🇹 Peter Steinberger
Pi agent coding
🇦🇹 Mario Zechner