Resources
Reference material, not gated PDFs.
Everything here is readable without giving us your email address. If it is useful, use it.
Reference architectures
How these systems are put together
Each project page documents the problem, the design decisions and the failure modes we hit.
LLM Router
A Go routing service that controls concurrency across llama.cpp workers, choosing whether a request runs now and where — based on live load, queue depth, latency and measured token throughput.
AI InfrastructureInfrastructure MCP
A self-hosted Model Context Protocol server that gives AI agents safe, audited access to real infrastructure — high-level tools instead of raw SSH.
Blockchain InfrastructureEthereum RPC Router
An intelligent load balancer for Ethereum RPC nodes with canonical-data guarantees, re-org detection, client-aware routing and native WebSocket proxying.
AI InfrastructureMulti-GPU LLM Provisioning
An Ansible playbook that deploys one llama.cpp inference server per GPU on a multi-GPU host — each with its own model, port, parameters and systemd unit.
Engineering write-ups
Guides and deep dives
Longer-form notes from production work, including the parts that went wrong.
Scaling an aggregation pipeline: from 41,000 queries a cycle to a handful
Designing a data-ingestion pipeline whose cost scales with what changed, not with the size of the dataset — batch loading, delta filtering, and cursor-based fan-out.
Dependency bots tell you what changed. They don't tell you if it matters.
Why we built an LLM-scored, bundle-aware upgrade pipeline instead of accepting the one-PR-per-package model Renovate and Dependabot default to.
Building an LLM inference layer that survives any single provider's outage
Why we treat LLM providers as an infrastructure dependency to route around, not a fixed integration — a circuit breaker, a fallback order, and a response layer built for the least standardized provider in the chain.
Service boundaries for a 13-service Ethereum mempool pipeline
Why decoding the mempool in real time is a distributed-systems architecture problem — a swappable message bus, a decode waterfall with graceful degradation, and service isolation enforced by convention.
Case studies
Problems, start to finish
What was broken, what we changed, and what we would do differently.
Architecting a 13-service pipeline to decode the Ethereum mempool in real time
Building a message-bus-connected microservice platform that turns raw pending-transaction calldata into structured MEV, gas-market and liquidation signal before a block ever confirms.
AI infrastructureQueue-based infrastructure for scoring, bundling and verifying dependency upgrades
An async worker architecture that turns changelog noise into a dependency-ordered upgrade plan, with a multi-provider LLM layer resilient to any single provider's outage.
Crypto markets infrastructureA tiered polling architecture for tracking nine exchanges in real time
Designing a multi-exchange monitoring platform that matches its infrastructure cost to what each exchange's API actually allows, instead of one uniform, worst-case polling strategy.
Compliance / fintech infrastructureBuilding a resilient compliance API on top of an unreliable government service
A per-country circuit breaker, canonical-identifier data model, and an isolated billing service — the platform engineering that turns a free, unreliable VIES endpoint into a dependable product.
Web3 infrastructureMaking Ethereum RPC correct under load and re-orgs
Replacing a round-robin balancer in front of a mixed Erigon/Geth/Reth fleet with a router that classifies every method and guarantees canonical data.
AI infrastructureMaking multi-GPU inference predictable instead of fast
Replacing even traffic distribution across llama.cpp workers with admission control based on live load, queue depth and measured throughput.
Platform engineeringGiving AI agents infrastructure access without giving them a shell
Replacing agent SSH access with an MCP server exposing inventory-driven, validated, audited operations.
Looking for something that isn't here?
We write up the problems we actually hit. If you are working through something specific — GPU serving economics, RPC tiering, Terraform state surgery — tell us and we will either point you at prior art or write it up.