Nathan Brewer
Full-Stack • IoT • Infrastructure • AI-Native
I don't sell hours. I sell directed inference.
12.6 billion tokens aimed at real problems.
12.6 billion tokens aimed at real problems.
[ scroll to enter ]
Chapter 01 // The Generalist
Master of all technology.
Lazy coder.
Lazy coder.
14 years on GitHub. 9 languages. Hardware, firmware, mobile, web, infrastructure.
The kind of engineer who can build anything from a PCB to a Kubernetes cluster
— but always built just enough to prove it worked, then moved on.
GitHub Contributions // 2022-2025 (pre-AI era)
70
2022
189
2023
210
2024
1,052
2025-26
← 5x jump
C++
C
JavaScript
TypeScript
Swift
Kotlin
Python
PHP
HTML/CSS
Eagle CAD
KiCad
ESPHome
Pulumi
Terraform
Docker
Chapter 02 // The Inflection
Same brain. Infinite throughput.
The generalist skillset wasn't the weakness — it was the latent advantage.
Knowing a little about everything meant knowing exactly where to point
the most capable AI models on the planet. The lazy coder became the
most efficient one.
Before // Pre-AI
Daily output50-100 LoC
Projects/day1 (maybe)
Contributions/yr~150
Context switchesPainful
BreadthWide but shallow
Weakness"Lazy coder"
→
After // AI-Native
Daily output4,123 LoC
Projects/day3.2 average
Contributions/yr1,052+ (accelerating)
Context switches64% of days, no friction
BreadthWide AND deep
SuperpowerDirected inference
Chapter 03 // The Receipt
12.6 billion tokens.
73 days. 48 repos. 358K lines.
73 days. 48 repos. 358K lines.
Not vanity metrics. Actual inference consumed building production systems
— infrastructure-as-code, IoT platforms, customer-facing applications,
mobile apps, and everything in between. Running 87% on Opus, the most
capable model available.
12.6B
Tokens Processed
124,622
API Calls
4,123
LoC / Day
48
Production Repos
87%
OPUS
Opus (87%) — Maximum capability
Sonnet (11%) — Fast iteration
Haiku (1%) — Quick lookups
Inference by Domain
Chapter 04 // The Vector
The trajectory is vertical.
Monthly GitHub contributions overlaid with daily token consumption.
The green is what the world can see. The magenta is the engine underneath.
Weekly Token Velocity (Last 4 Weeks)
Week of Jan 26
Week of Feb 2
Week of Feb 9
Week of Feb 16
Chapter 05 // The Lab
Currently shipping.
PCBs. Firmware. Mobile apps. Cloud platforms. Smart contracts.
All of it real. Most of it live.
DropLink
Meshtastic remote release mechanism. PCB design to iOS app to shipping product.
Off-Grid Radio Network
People-powered mesh radio. Off-grid comms for everyone. Token economy in the works.
AI Dev Platform
Self-hosted AI dev platform. Talk to it, build what you want. Every project gets its own container.
IoT Platform
Full-stack IoT platform. AWS IoT Core, hardware crypto chips, Pulumi/Terraform IaaC. Lambda, ECS, EC2, RDS, S3, EventBridge. Production.
BLE Lock Protocol
Reverse-engineered smart lock BLE protocol. 73 opcodes. Full Swift SDK and iOS app. No cloud.
Mesh Client
Native iOS, iPadOS & macOS client for Meshtastic. SwiftUI, BLE, mesh networking.
Walking Pad + AI
MCP server that lets Claude control your walking pad. AI picks the speed based on task complexity.
Ohm School
Bluetooth multimeter companion for iOS & Apple Vision Pro. Yes, visionOS.
HID-HOP
nRF52840 BLE-to-USB HID bridge. Custom firmware, Android app, iOS app. Published on both app stores.
Mega-Sensor Beacon
ESP32 sensor platform. Air quality, presence, scale, IMU, ToF, color, CO2, LoRa. One board.
Access Controller
STM32 access control firmware. Signed auth protocol, BLE provisioning, calendar rules, OTA updates.
On-Device Whisper
Native macOS menu bar speech-to-text. Local Whisper model. Hotkey triggered. Zero cloud.
Voice Clone Engine
Local AI voice synthesis. F5-TTS model in memory for 1-3s inference. Embeddings + semantic search.
Mesh Token Economy
Smart contracts. Token economy for mesh network participation. Minting my own future.
NoFlixGiven
Decentralized media lending. Own it. Lend it. Never kneel. Smart contracts, IPFS, WASM streaming.
Hardware Security Research
Reverse-engineered commercial IoT device. Found API exposing BLE credentials for entire fleet.
// this is not a portfolio. this is a tuesday.
Chapter 06 // Work With Me
Hire the whole team.
One engineer. Full-stack output. Infrastructure to IoT to frontend.
I bring the AI compute, the context, and 14 years of building everything
from circuit boards to cloud platforms.
172M
Tokens / Day
3.2
Projects / Day
1,707
API Calls / Day