← oshalusirelaystack.io ↗
Case study

Relaystack

A modular AI engine with installable skills that execute real outcomes. I am building it as founder and CTO, launching Q3 2026.

Founder / CTO · 2026 · Relaystack · Web
Overview

Relaystack is an AI platform that executes real-world outcomes through composable, installable skills — not just conversation.

The architecture treats AI models as a runtime, not a product. Skills are discrete units of capability that combine to do things: schedule meetings, process invoices, monitor infrastructure, and report back. Each skill is versioned, testable, and replaceable.

As sole engineer, I designed the monorepo structure, the skill contract API, the queue system, and the orchestration layer from scratch — then built against them simultaneously.

The constraint

Most AI products stop at the conversation. Getting an LLM to generate text is table stakes. The hard part is reliability: running skills that touch real systems, recover from failure, and audit what they did. That is the problem Relaystack is built to solve.

Highlights

Modular skill system

Skills are npm packages that implement a typed contract. They can be installed, updated, or swapped without touching the engine. The platform grows without the core changing.

Durable queue architecture

Every skill execution is a BullMQ job with retry, backoff, and dead-letter handling. If the process crashes mid-skill, the job resumes — not restarts. Transient infrastructure failures do not become user-facing errors.

Multi-agent orchestration

Complex tasks decompose into sub-agents that run concurrently, report back, and can spawn further sub-tasks. The orchestrator never blocks on a single model call, and every step is logged for auditability.

Stack
Next.js · TypeScript · Node.js · Turborepo · BullMQ · Redis · PostgreSQL · OpenAI & Anthropic SDK · Docker · AWS · GitHub Actions

Relaystack is the platform I wanted to exist. It will be in production Q3 2026 — built to the standard I hold everything else to.