Projects

A selection of projects I've worked on.

ProseForgeFeatured
Problem:

Content creators need a streamlined way to research, ingest, and generate stories from multiple sources. ProseForge is a writing platform, not a content automation framework.

Role:

Founder / Architect

What I did:
  • -Built Go backend with Chi router, PostgreSQL, and River job queue
  • -Integrated AI story generation via Ollama/RunPod
  • -Created Vue.js frontend for content management
Outcome:

Full-stack content automation platform powering proseforge.ai

GoPostgreSQLVue.jsTypeScriptDockerTerraform
ProseForge WorkbenchFeatured
Problem:

AI agents need a structured way to read, review, and improve stories on ProseForge without hand-rolling HTTP calls for every workflow.

Role:

Founder / Architect

What I did:
  • -Built Go CLI and MCP server sharing a common service layer
  • -Generated typed API client from the ProseForge OpenAPI spec via oapi-codegen
  • -Released cross-platform binaries (darwin/linux × amd64/arm64) via GoReleaser
Outcome:

BYOAI client that lets any AI agent act as an author or reviewer on ProseForge

GoMCPOpenAPIoapi-codegenCobraGoReleaser
ProseForge iOS App
Problem:

Users need native iOS access to browse and read ProseForge stories.

Role:

Founder / Architect

What I did:
  • -Built cross-platform app with .NET MAUI targeting iOS, Android, macOS
  • -Generated type-safe API client via NSwag/OpenAPI
  • -Implemented MVVM architecture with dependency injection
Outcome:

Native companion app for ProseForge on iOS

.NET MAUIC#XAMLOpenAPI
ProseForge Android App
Problem:

Users need native Android access to browse and read ProseForge stories.

Role:

Founder / Architect

What I did:
  • -Built cross-platform app with .NET MAUI targeting iOS, Android, macOS
  • -Generated type-safe API client via NSwag/OpenAPI
  • -Implemented MVVM architecture with dependency injection
Outcome:

Native companion app for ProseForge on Android

.NET MAUIC#XAMLOpenAPI
ProseForge TTS Worker
Problem:

Narrating story audiobooks at scale needs a TTS pipeline that's fast, cheap, and doesn't drag a Python runtime into every deploy.

Role:

Solo Developer

What I did:
  • -Ported Kokoro-82M ONNX inference to pure Go — no Python dependency
  • -Built context-aware homograph disambiguation with Misaki dictionaries and Flite LTS fallback
  • -Deployed as RunPod serverless with zero cold-start and WAV/MP3 output
Outcome:

Pure-Go serverless TTS worker powering ProseForge audiobook narration

GoONNX RuntimeKokoro-82MRunPodFFmpegDocker
Blackjack
Problem:

Demonstrate cross-language integration from low-level game engine to modern web UI.

Role:

Solo Developer

What I did:
  • -Implemented core game logic in C++ with C ABI wrapper
  • -Built ASP.NET Minimal API for game server
  • -Created Vue.js frontend with multiple card themes
Outcome:

Full-stack game demonstrating C++ → C# → Vue.js interop

C++C#ASP.NETVue.jsDockerNginx
ProseForge Marketing Stack
Problem:

Creating narrated demo videos requires tedious manual audio sync and publishing.

Role:

Solo Developer

What I did:
  • -Built MCP server for Claude Code integration
  • -Automated TTS generation with macOS voice and Gemini API
  • -Integrated FFmpeg for audio/video mixing with timing validation
Outcome:

Automated pipeline from markdown scripts to published YouTube videos

PythonFFmpegMCPPlaywrightYouTube API
Drop Jockey
Problem:

Build a Connect-4 game with pluggable AI agents and clean architecture.

Role:

Solo Developer

What I did:
  • -Designed pure game engine with zero runtime dependencies
  • -Created pluggable player system (Human, Random, Heuristic, LLM)
  • -Built dual renderers: React web UI and terminal curses interface
Outcome:

Clean-architecture game with swappable AI players including LLM support

TypeScriptReactViteVitestPlaywrightOllama
CryptoWatch
Problem:

Track cryptocurrency prices and market data in real-time.

Role:

Solo Developer

What I did:
  • -Built C# web application with MCP codegen tooling
  • -Integrated Grafana monitoring system for observability
  • -Implemented load testing with documented performance results
  • -Created self-documenting workflow using Puppeteer
Outcome:

Real-time cryptocurrency tracking platform with integrated monitoring

C#ASP.NETGrafanaPuppeteerDocker