My AI-first dev workflow — the underlying stack powering how I build, scale, and automate.
Every tool here earns its place: no fluff, no bloat — just systems that let me move fast and ship clean.
AI Code Assistants
OpenCode
Primary AI code assistant
Claude
Secondary AI assistant — Hermes configured
GitHub Copilot
Tertiary inline completions
Cursor Agent
IDE-level alternative when needed
Memory & AI Systems
NotebookLM
Deep context and RAG for long documents
Hermes + Hindsight
Custom agent with cloud memory layer
Supermemory
Persistent knowledge layer
Ruflo
Custom MCP: agent orchestration layer
fullstackskills
Custom MCP: 21-agent scaffolding system
Context7
Custom MCP: live docs retrieval inside chat
Languages & Runtimes
Node.js / pnpm
Primary JS runtime and package manager
Rust / cargo
Systems programming and CLI tooling
Bun
Fast JS runtime for edge-ready scripts
Python / uv
AI/ML scripts, fast dependency management
Java / SDKMAN
Enterprise integrations and JVM tooling
TypeScript
Strict typing across the entire stack
Editors
VS Code
Primary editor with full extension ecosystem
Zed
Fast, GPU-accelerated editor for focused sessions
Neovim
Terminal-native editing and scripting
Cursor
AI-native editor for high-context sessions
DevOps & Databases
Podman
Rootless container runtime — primary choice
PostgreSQL
OLTP workhorse for relational data
Supabase
Backend-as-a-service with Postgres
Redis
Caching, pub/sub, and session store
NeonDB
Serverless Postgres for edge workloads
Terminal & Power Tools
zsh + Starship
Shell and prompt for maximum clarity
RTK
Custom token killer — 60–90% token savings on dev ops
lazygit
Terminal UI for git — fast and visual
eza
Modern ls replacement with icons
rclone
Cloud storage sync and backup automation
ngrok
Instant secure tunnels for local dev