Portfolio index

Selected systems & case studies

Eight production-minded projects spanning Sui Web3 (agent treasuries & social dApps), fraud detection, document RAG, real estate SaaS, dual-engine TTS, and AI-assisted CLI tooling. Each write-up covers problem framing, architecture choices, and engineering tradeoffs.

Web3 · Sui
W1 AI billing · Move

SEAL

Sui Move TypeScript Next.js x402
Full case study arrow_forward GitHub

SEAL is a non-custodial billing layer for AI teams on Sui. Deposit once, set hard spend caps enforced by Move smart contracts, and route API calls to Groq, OpenAI, Anthropic, or x402-compatible services through a single API key.

Architecture splits into three layers: a TypeScript gateway (auth, provider routing, velocity tracking, batch settlement), on-chain contracts (deposit/withdraw, caps, authorize_call, pause), and a Next.js dashboard for wallet connect, treasury setup PTBs, key management, and anomaly alerts. Users sign treasury ops; the gateway only settles.

W2 Agent treasuries

Otter

Sui Move Node/TS gateway TS + Python SDK
Full case study arrow_forward GitHub

Otter (Autonomous Agent Treasury Protocol) gives every AI agent its own on-chain treasury — a Sui object that holds Coin<SUI>, enforces spending policies, and can be reclaimed atomically. No central custodian; no opaque credit-card billing for agents.

Master treasuries spawn child agents with sub-budgets; daily/monthly/single-spend caps and provider allowlists are enforced in Move. The gateway settles each inference via authorize_agent_call, serializes per-treasury writes to avoid object locks, and exposes TypeScript and Python SDKs for agent developers.

W3 Social dApp

DSpace

React 19 Sui dapp-kit Firebase Vite
Full case study arrow_forward GitHub Live site

DSpace (SuiPod Chat) is a hybrid decentralized collaboration platform: Sui wallet identity and on-chain pod membership, plus Firebase Realtime Database for instant messaging.

Users create pods, add members by wallet address, chat in real time, and send SUI directly to pod members without leaving the UI — bridging social product UX with on-chain payments and access control via @mysten/dapp-kit.

AI · Fullstack · Tools
01 AI · Fintech risk

Asguard

High-volume fintech environments need fraud decisions that are fast enough for live payment flows and explainable enough for compliance review. Asguard is a real-time fraud detection pipeline that scores transactions with layered rules, enriches them with AI risk assessment, and emits structured alerts with natural-language summaries.

The system prioritizes low-latency paths for clear-cut decisions, escalates ambiguous events for deeper model analysis, and keeps investigator context in-band so teams spend less time reconstructing “why” a transfer was flagged.

Go Gin Firebase LLM inference PostgreSQL
Full case study arrow_forward Live site
02 RAG · Document intelligence

Azeru

Unstructured PDFs are slow to search and easy to misread under time pressure. Azeru is an enterprise RAG platform that ingests documents, chunks them for embedding quality, stores vectors for semantic retrieval, and answers questions through a conversational interface with source-aware responses.

Backend processing is built in Go for throughput; the operator UI is Next.js for fast iteration and validation loops. Inference is routed through high-speed LLM providers so retrieval + generation stays interactive rather than batch-only.

Go Next.js Groq AI Vector search Docker
Full case study arrow_forward Source
03 SaaS · Real estate

Hauser

Hauser is a real estate marketplace oriented toward Nigerian property professionals — agents, landlords, and tenants. The product combines listing discovery with role-aware onboarding so each persona lands in the right workflow without manual admin setup.

Built on Next.js with Firebase (Firestore, Cloud Functions), it supports dynamic listings, real-time updates, automated image optimization, and click analytics for premium tiers. The goal: reduce agency friction and give operators a lightweight SaaS control plane instead of a static directory.

Next.js Firebase Firestore Cloud Functions
Full case study arrow_forward Live site
04 AI audio · TTS

Koe

Next.js Azure TTS WebSocket Docker · Piper
Full case study arrow_forward

Text-to-speech products usually force a single vendor tradeoff: cloud quality and cost, or offline privacy with weaker voices. Koe is a dual-engine TTS studio that runs both — Microsoft Azure Neural voices for premium cloud synthesis, and offline Piper TTS via Dockerized local inference when data should not leave the machine.

Audio is streamed in real time over WebSockets. Engine selection is modular so operators can switch at runtime based on latency budget, per-character cost, or privacy requirements — useful for content studios, accessibility tools, and air-gapped environments.

05 CLI · Devtools

Vpipe

Go Groq OpenAI Anthropic
Full case study arrow_forward

Pasting build logs into a chat model is common — and dangerous when secrets hide in stack traces. Vpipe is a Go CLI that pipes compiler and runtime errors into multi-provider LLM APIs (Groq, OpenAI, Anthropic) and returns actionable fix suggestions without requiring a browser workflow.

Before any external call, auto-sanitization masks 20+ sensitive patterns (keys, tokens, connection strings). Smart truncation respects provider token limits so large logs remain usable without silent context blowouts — a security-aware take on AI-assisted debugging.

Want the architecture walkthrough live?

Happy to discuss tradeoffs, stack choices, and what I’d harden next in a technical interview.

Email Kennedy