Skip to content
View awdemos's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report awdemos

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
awdemos/README.md

Quotidie est ratio plenae laetitiae in miraculo vitae
Every day is the reason for complete joy in the miracle of life

Andrew (awdemos) — AI Engineering, Rust Agents, OpenCode Plugins & Local LLM Tools

Open-source AI infrastructure by Andrew: Rust agent orchestrators, OpenCode plugins, local LLM tooling, NVIDIA GPU utilities, and experimental operating systems. Building production-grade agents from scratch.

👋 About

I build everything from scratch — open-source systems, commercial AI infrastructure, and hands-on consulting.

Linux Rust NVIDIA Kubernetes Go Python Vibe Coding Agency Book a Call


🚀 The Pitch

I build the full stack — systems, languages, and developer tools — almost entirely in Rust, almost entirely from scratch.

An operating system. A text editor. An AI coding assistant. A blockchain. A borrow checker. An agent orchestrator. Neural networks. Programming languages. Simulators for synthetic life.

Most of it is open source; the commercial products and services below help me keep building in public.

Personal stretch goal: Build every tool I rely on — nothing I use should be something I couldn't have written myself. Full ownership of the stack.

I give all of this away for free as a shoutout to all the known and unknown open source hackers out there who influenced me, either directly or indirectly.


💼 Products & Services

I run Vibe Coding Agency — shipping production AI infrastructure, agentic systems, and GPU cloud access for teams that need to move fast.

Offering What it is Investment Get started
UltraWork GPU cloud chat & console for AI inference $399/mo Sign up →
KV Cache Store Hosted KV-cache storage & sharing for LLMs Pay-as-you-go Dashboard →
kvcdn-cli Open-source CLI to generate, verify, quantize, and upload KV caches Free / OSS Install →
Open Superintelligence Stack The same OpenCode environment we use to ship $199/mo Subscribe →
Hourly Vibe Coding Hands-on AI infrastructure pair-programming $199/hr Book hours →
Monthly Retainer 10 hours of dedicated agency support per month $1,999/mo Start retainer →
Private Discord Community Members-only community & early access $4.99/mo Join →

🏆 The Trinity — Full Stack Ownership

These three represent my core thesis: if you use it every day, you should own it.

Project What Why It Exists
RegicideOS Rust Foundation OS for higher-layer AI products — Gentoo + BtrFS + COSMIC Desktop, every layer optimized for ML. Variants: RegicideOSArch (available now) and musl-based builds (future) Because an OS that doesn't understand GPUs is obsolete
openlibertas Rust Terminal-based AI coding assistant with multi-provider, MCP tools, multi-agent delegation, voice mode Because your coding assistant should be yours — free forever, no subscriptions
neoxide Rust Neovim-inspired terminal editor with LSP, tree-sitter, Lua plugins, splits, registers, macros, marks Because every developer deserves an editor that matches how they think

🧠 Selected Open Source

A curated set of projects that power my commercial work and research. See the full awdemos org for experiments in blockchain, languages, simulations, and games.

🤖 Agentic Work

These projects form the core of how I build, orchestrate, and reason with AI agents — from terminal assistants to distributed multi-agent systems.

Project Description Lang
openlibertas Full AI coding assistant — 15 agent personas, MCP tools, voice, session management Rust
kairo Agentic orchestrator — model council routing, ReAct agents, WASM sandboxing, DAG workflows Rust
Xfiles Plan 9-inspired agent communication hub — VFS namespaces, quantum-mode routing, MCP Rust
zerochain Filesystem-native multi-agent workflows — content-addressed, deterministic, zero-unsafe Rust Rust

✏️ Developer Tools

Project Description Lang
neoxide Neovim-inspired terminal editor — LSP, tree-sitter, Lua plugins, splits, macros Rust
opencode-memento Context preservation across AI coding sessions TypeScript

🖥️ Systems & GPU

Project Description Lang
RegicideOS AI-native Rust Linux distro — Gentoo + Cosmic Desktop, GPU-optimized kernel Rust
RegicideOSArch Arch Linux variant of RegicideOS — bootable QCOW2, COSMIC, Dagger pipeline Rust/Shell
cuda-oxide Custom rustc backend for CUDA kernels in pure Rust — single-source Rust → PTX Rust

🏢 Enterprise & Research

Project Description Lang
enterprise-ai-atlas-profile A curated index of enterprise-grade AI systems, patterns, and reference architectures for production AI factories Markdown

📂 Production Demos & Reference Patterns

Not everything is scratch-built. Some things are battle-tested patterns you can actually use in production:

Demos Repo

  • Kubernetes — 100+ deployment patterns, Cilium eBPF, multi-cluster federation
  • LLM Infrastructure — RAG pipelines, fine-tuning, multimodal benchmarks
  • KV Cache Infrastructure — Generate, quantize, and host KV caches for LLMs with kvcdn-cli + KV Cache Store
  • CI/CD — Dagger Go pipelines, container-native builds, security scanning
  • IaC — Pulumi (Go/TypeScript) for Azure & AWS multi-tenant infrastructure
  • Rust — Matrix ops, CLI boilerplate, async patterns that don't leak memory
git clone https://github.com/awdemos/demos.git

🧭 How I Think About Building

Reproducible. Observable. Composable.

I design systems from first principles. Small tools that do one thing well and compose cleanly — the Unix way, but for the AI era.

  • I don't trust black boxes. If I can't audit it, I don't ship it.
  • I prefer code over YAML. If it can be code, it should be code.
  • I believe in AI sovereignty. Models you own, data you control, infrastructure you can audit.
  • I value memory safety. Not because Rust told me to, but because debugging segfaults at 3am is a waste of a life.
  • I'm a huge fan of tried and true principles and underappreciated technologies. I can work on everything from a PDP-11 to FreeBSD and post-Linux kernels with equal fluency.

My formative years were spent on Slashdot and deep in open source culture — that ethos of transparency, collaboration, and building in public is still how I work today.

What Kimi 2.7 has to say about my coding style: A technically deep, curiosity-driven engineer with strong systems programming instincts, a Rust-centric toolchain, and heavy involvement in AI/automation tooling. Likely experiments broadly and iterates fast rather than shipping polished products. Possible backgrounds: systems engineer, game dev, AI/ML tooling, or indie hacker.


🎖️ Background

Now AI Factory Lead at a Fortune 500 — led technical collaborations with NVIDIA, building AI infrastructure that ships reliably, safely, and fast
2024–2025 Lead AI Infrastructure Engineer, Helix Center for Applied AI
Earlier Cycorp Inc. — reported to Dr. Doug Lenat, symbolic AI for defense & healthcare
Way back Sold Linux supercomputers · Built Top 500 HPC systems · Infrastructure at OpenDNS & Wikimedia Foundation
Certifications NVIDIA DGX SuperPOD · AI Infrastructure · InfiniBand · NVIDIA Pro Certifications · Agentic Certified
Awards Award-winning developer
Community Founder, Enterprise AI Atlas
Aspiration I aspire to motivate, lead, teach, and inspire every single day and it is not so much about me but the unbelievable mentors and colleagues whose shoulders I stand on who showed me the way. I don't believe in limitations — I only believe in the limits of imagination.

⚡ Best in Class

  • Best-in-class infrastructure engineering
  • The fastest CI/CD on the planet
  • Extreme performance optimization
  • Extreme Linux and open source security practices

🌌 The Bigger Picture: AI Pangaea

A lot of this work is anchored in one idea: the future of intelligence is unified, not fragmented.

I'm exploring what it means to build AI Pangaea — the convergence of distributed intelligence islands into a more cohesive, secure, and capable continuum:

  • Superintelligent entities with persistent memory and recursive self-improvement
  • Security at every layer — sandboxing, guardrails, consensus verification, confidential execution
  • Memory & continuity across sessions, devices, and intelligence islands

📄 AI Pangaea: Unifying Intelligence Islands — arXiv:2509.17460


🤝 Let's Connect

If you're working on something in the intersection of systems, AI, and security, I'd genuinely love to hear about it.


© 2026 Andrew White — Built with curiosity, caffeine, and a deep distrust of complexity for its own sake.

Pinned Loading

  1. awdemos awdemos Public

    This is my professional portfolio demonstrating my interests in AI, DevOps, and software development.

    Shell 5

  2. opencode-memento opencode-memento Public

    OpenCode plugin that preserves project context across sessions, automatically injecting relevant prior work into compaction

    TypeScript 9 1

  3. symbolic_ai_elisp_knowledge_base symbolic_ai_elisp_knowledge_base Public

    A simple re-imagining what Cyc could be in an open source implementation.

    Emacs Lisp 7

  4. zerochain zerochain Public

    This is a Multi-agent orchestration tool using text files as Agents

    Rust 5 1

  5. opencode-superpowers opencode-superpowers Public

    OpenCode skill installer for the Superpowers workflow

    JavaScript 3

  6. RegicideOSArch RegicideOSArch Public

    RegicideOS Arch, a BTRFS based OS with Cosmic Desktop and AI out of the box.

    Shell 3 1