Skip to content
tamldPublic

About

Read Me Profile

Resources

Stars

1 star

Watchers

1 watching

Forks

Latest commit

Β 

History

18 Commits

Folders and files

NameName
Last commit message
Last commit date
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

πŸ‘‹ Hi, I'm Tam Le Duc

Typing SVG

LinkedIn Email Buy Me a Coffee YouTube

11+ Years Zero-Trust PRs Merged Homelab SRE

Profile Views Followers


"I don't build systems to impress β€” I build them to quietly endure.
From bare-metal infrastructure to AI agent governance: solid systems begin with steady hands."


πŸŒ‰ The Bridge: Infrastructure Heritage ➜ AI Agent Architecture

With 11+ years in IT Operations & Systems Engineering (bare-metal virtualization, multi-site enterprise networking, and zero-downtime disaster recovery), I approach Artificial Intelligence from a First-Principles engineering perspective.

While most treat AI as prompt-driven magic, I treat it as an untrusted, high-velocity compute layer that demands:

  • Deterministic Guardrails: Hard runtime boundaries, process sandboxing, and write receipts instead of hoping the LLM "behaves."
  • Epistemic Integrity: Enforcing a strict separation between hypothesis ([HYPO]) and physically proven evidence ([PROVEN]).
  • Zero-Root Infrastructure: Multi-layer perimeter defense (Edge WAF $\rightarrow$ Traefik v3 $\rightarrow$ CrowdSec $\rightarrow$ Passkey FIDO2) with bounded autonomous self-healing.

πŸ›οΈ Ecosystem Architecture

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚              COGNITIVE LAYER: Governed Second Brain                     β”‚
β”‚    β€’ SSoT Knowledge Base & Deterministic Orchestrator (wiki.py)          β”‚
β”‚    β€’ ADLC Finite State Machine & Gate D Deep-Why Verification           β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                     β”‚ Issues Path-Scoped Write Receipts
                                     β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚              EXECUTION LAYER: g8s (The Gatekeepers)                     β”‚
β”‚    β€’ Zero-Trust Go Binary Runtime for AI CLI Workers                    β”‚
β”‚    β€’ Capability Dropping, Subagent Sandboxing & Supervisor Fix Loop     β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                     β”‚ Controlled Action / Code Changes
                                     β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚              OPERATIONS LAYER: AI-Assisted Homelab Platform (IaC)       β”‚
β”‚    β€’ Bare-Metal Proxmox VE, Rootless Podman, Tailscale Zero-WAN Mesh    β”‚
β”‚    β€’ Autonomous SRE Butler Agent: CTI Ingestion, SBOM & LogSQL Hunting   β”‚
β”‚    β€’ Human-in-the-Loop (HITL) HMAC-SHA256 Telegram Approval Cards       β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

πŸš€ Flagship Projects (Open Source & Public Runtimes)

πŸ›‘οΈ g8s (The Gatekeepers)

A Lightweight, Zero-Trust Process Execution & Capability Harness for AI Agent CLI Workers
β€œk8s orchestrates your compute containers; g8s orchestrates your AI subagents.”
Go Version Release GitHub Stars License: MIT Platform

  • Two-Tier Agent Harness: Enables high-tier Brain orchestrators (Claude 3.7 / Opus / GPT-4o) to safely dispatch mechanical tasks to lightweight CLI workers (Antigravity CLI, Claude Code CLI, Gemini CLI) under strict sandbox constraints.
  • Cryptographic Write Receipts: Grants time-limited, path-scoped write authority (Schema v3) to prevent unauthorized file mutation and codebase drift.
  • Supervisor Fix Loop: Automated execution verification, metrics ingestion, and self-correcting agent loops.

Production-Inspired Reference Architecture & SRE Automation for Bare-Metal Homelabs
Shell GitHub Stars Traefik Podman CrowdSec VictoriaLogs

  • 3-Tier Balanced Architecture: Perimeter Ingress & Identity (Traefik v3, CrowdSec, Tailscale Mesh, Dual-Tier IAM) $\rightarrow$ AI Gateway & Operations Plane (LiteLLM, SRE Butler Agent) $\rightarrow$ Observability & GitOps Core (VictoriaLogs, VictoriaMetrics, Age Encryption).
  • Dual-Tier Zero-Trust IAM: Biometric Passkey FIDO2 via Pocket ID combined with ForwardAuth proxy via Authelia and LLDAP.
  • Closed-Loop SRE Automation: SRE Butler periodically polls CTI feeds (CISA/GHSA), performs $O(1)$ local SBOM matching, executes retroactive forensic hunts via VictoriaLogs LogSQL, and dispatches HMAC-SHA256 signed Telegram approval cards (300s TTL).
  • Zero-Spam GitOps Engine: Automated hypervisor drift reconciliation every 15 minutes with content-addressable SHA-256 suppression and Age Zero-Knowledge secrets encryption.

πŸ›‘οΈ defense-in-depth

Governance Middleware Between AI Agents and Your Codebase
TypeScript GitHub Stars Node.js

  • Acts as an automated defense layer preventing AI agents from generating hollow artifacts, executing unverified cowboy commits, and polluting Single Sources of Truth (SSoT).
  • Enforces strict contract schemas and validation checks before mutations reach Git repositories.

πŸ€– ContribAI (Contributor β€” original by @tang-vu)

Autonomous Open Source Contribution Engine
Rust MCP

  • Contributed to autonomous multi-agent pipelines for discovering open-source issues, synthesizing reproducible tests, and authoring pull requests.
  • 9 PRs successfully merged across 21+ open-source repositories.

πŸ”’ Engineered Systems & Production Labs [Case Studies]

(Architectural blueprints and private self-hosted fleets operated under strict Zero-Leakage OpSec standards)

🧠 Personal Cognitive OS & Governed Second Brain [πŸ”’ Architecture Case Study]

  • Challenge: Scaling personal knowledge and technical decision-making across dozens of AI agent sessions without context drift, unverified assumptions, or knowledge rot.
  • Architecture & Mechanism:
    • Engineered a deterministic Python runtime (wiki.py) functioning as a physics engine for the vault: forces orientation, JIT similarity searching, and epistemic labeling before any file modification.
    • ADLC (Agentic Development Life Cycle): Enforces finite state machine (FSM) transitions and Red Test Proof sections on engineering plans, backed by automated Git pre-commit gates.
    • Memory Distillation Pipeline: Background daemon scanning execution logs to distill ephemeral agent interactions into proven axioms with Zero DLP leakage.
  • Impact: Zero hallucinated rules across 500+ documentation nodes; 100% auditable knowledge lineage.

🏠 Autonomous SRE Homelab Fleet [πŸ”’ Production Lab]

  • Challenge: Managing a high-availability bare-metal virtualization cluster hosting 20+ services with zero public exposure and sub-second incident triage.
  • Architecture & Mechanism:
    • Zero-WAN Exposure Law: Management interfaces (Proxmox VE, RouterOS, VictoriaLogs) strictly restricted to internal LAN and Tailscale Mesh VPN (Zero-Trust Encrypted Mesh).
    • Dual-Plane Observability: Synthetic uptime monitoring separating compute plane ([LAN] internal container health) from edge ingress ([WAN] public domain health), isolating routing vs service failures in under 2 seconds.
    • Single Authority DHCP: Centralized RouterOS static lease binding as the single source of truth for container network identities.
  • Impact: 99.9% fleet availability, zero unauthorized ingress attempts, and under 5-minute automated disaster recovery.

πŸ“Œ All Projects & Tools

πŸ€– AI Agents & Governance
  • πŸ›‘οΈ g8s (The Gatekeepers) β€” Zero-Trust process execution & write receipt harness for AI CLI workers
  • πŸ›‘οΈ defense-in-depth β€” Governance toolkit for AI coding agents
  • 🧩 mcp-orchestration-framework β€” Multi-agent SoT bootstrap PoC using Model Context Protocol
  • ✨ awesome-prompt-engineering β€” Curated prompts and guardrail patterns for AI + DevOps automation
  • πŸ€– ContribAI (fork/contributor) β€” Autonomous OSS issue discovery and PR contributor (9 PRs merged)
πŸ—οΈ Infrastructure, SRE & IaC
  • πŸ—οΈ IaC β€” AI-Assisted Infrastructure Operations Platform & SRE automation for bare-metal homelabs
  • 🌐 foss-virtualization β€” Open-source guide to virtualization & containerization
πŸ› οΈ Utilities & Tools
  • 🎢 tuneflow β€” Elegant, elderly-friendly YouTube audio downloader & player
  • πŸ’» cmdToolForHelpdesk β€” Windows IT support automation toolkit (batch scripts)
  • πŸ” hash-checker β€” Cross-platform Rust hash checker (CLI + GUI)
  • πŸ” proxy-checker β€” Proxy availability checker with Telegram reporting
  • πŸ“₯ awesome-download-manager β€” Curated download manager reference guide

πŸ—οΈ Technical Capabilities & Infrastructure Heritage

A decade of bare-metal and cloud operations providing the bedrock for scalable AI systems.

Domain Technologies
Systems & Languages Go Rust Python TypeScript Bash PowerShell
AI Agent & Protocol Systems MCP LiteLLM Claude Code Antigravity
Virtualization & Containers Proxmox Docker Podman Kubernetes VMware
IaC & Automation Terraform Ansible Vagrant GitOps
Security & Networking Zero Trust Tailscale CrowdSec Traefik Fortinet
Observability & SRE VictoriaLogs VictoriaMetrics Grafana Zabbix Prometheus

🧭 Engineering Principles

  • Mechanism over Prompting β€” Don't instruct AI to be careful; build guardrails and process harnesses that make violations impossible.
  • Evidence over Plausibility β€” If it isn't verified by an execution command or physical log, it remains a hypothesis ([HYPO]).
  • Stability over Complexity β€” Fewer moving parts, zero spurious drift, and architectures designed to quietly endure.
  • Document along the Way β€” Systems outlive their builders; code without architectural context is technical debt.

πŸ“Š GitHub Stats

GitHub Stats Top Languages
GitHub Streak

About

Read Me Profile

Resources

Stars

1 star

Watchers

1 watching

Forks

Releases

Packages

Contributors