Projects

Loading projects…

Featured Projects

6 projects

CareerOS

Private product with public evidence · public-careeros

Problem
Resume versions and recruiting history drift apart without evidence.
What I Built
Built a C# and PostgreSQL workspace over versioned resumes, recruiting history, and user corrections, with human review before any update.
Impact
Passed 118/130 regression contracts (90.8%) with 0 unsafe automatic mutations.
C#PostgreSQLAI AgentsEvaluation

Token Bar

Public native macOS utility · token-bar

Problem
Claude Code and Codex split usage across separate local sources.
What I Built
Built a native menu bar app for quota windows, local activity, cost estimates, and stale-state recovery.
Impact
Keeps both providers visible through partial failures without uploading raw transcripts.
SwiftSwiftUIAppKitmacOS

OAuth 2.0 Security Reference

Public security reference · Next.js-OAuth2-Template

Problem
Email matching can enable account takeover and leave OAuth replay gaps.
What I Built
Built provider-first identity, verified-email checks, one-time PKCE and state, rotated Redis sessions, and rate limits.
Impact
Tests cover replay, email collisions, concurrent callbacks, session rotation, redirects, and role downgrades.
Next.jsPostgreSQLRedis

Agent Sandbox Eval

Public evaluation framework · agent-sandbox-eval

Problem
Agent evaluations need reproducible tasks and isolated execution.
What I Built
Built 25 sandboxed tasks with deterministic grading, replay, and hardened Docker controls.
Impact
Oracle and local controls score 25/25; the no-op control scores 0/25.
PythonDockerAI AgentsEvaluation

Boring Agent Memory

Public memory infrastructure · boring-agent-memory

Problem
Agents need local recall without replacing source files or crossing workspace boundaries.
What I Built
Built SQLite FTS5/BM25 retrieval with provenance, freshness checks, redaction, and workspace filters.
Impact
Across 120 synthetic queries: 0.990 Recall@1, 0.995 MRR, and 0 privacy leaks.
PythonSQLiteFTS5Retrieval

LLM Inference Acceleration Playground

Public benchmark toolkit · llm-inference-acceleration-playground

Problem
Inference comparisons fail when workloads, hardware, or run artifacts differ.
What I Built
Built streaming load tests, latency reports, KV-cache estimates, GPU telemetry, and claim-audit gates.
Impact
Excludes mock, incomplete, and incomparable runs from performance rankings.
PythonLLM ServingEvaluationGPU Telemetry

Other Projects

8 projects

BongoCat

A native macOS desktop companion that reacts to keyboard, pointer, mouse, and game-controller input using SwiftUI, AppKit, Metal, and Live2D Cubism.

SwiftAppKitMetalmacOS

Sequential Recommendation Benchmark

Team offline benchmark

A team benchmark comparing MostPopular, ItemCF, NeuMF, and SASRec for leave-one-out next-item prediction on the KuaiSAR short-video interaction dataset.

PythonPyTorchRecommendation SystemsSASRec

cc-lite

Public research baseline

An AlphaZero-style Xiangqi research baseline with a legal-move engine, PyTorch policy-value CNN, legal policy masking, PUCT MCTS, self-play, training, and engine distillation.

PythonPyTorchMCTSXiangqi

SFML Graphing Calculator

Graphing_Calculator_SFML

A C++17 and SFML graphing calculator with expression parsing, RPN evaluation, interactive plotting, expression history, and headless tests.

C++SFMLParsingComputer Graphics

Tripemini

A 48-hour multimodal food and travel MVP with bounded Gemini inference, structured TypeScript outputs, validation, deadlines, rate limits, and concurrency controls.

TypeScriptNext.jsGeminiVercel

Website Image Downloader

Website-Image-Downloader

A bounded Next.js ingestion service with DNS pinning, redirect revalidation, SSRF and DNS-rebinding defenses, private-address blocking, timeouts, and deterministic security tests.

TypeScriptNext.jsSecurityAutomation

SQL in C++

SQL

A C++17 paged storage engine with a CLI DSL, 4 KB checksummed pages, persistent B+ tree indexes, WAL-backed atomic writes, copy-first migration, and sanitizer-backed crash-recovery tests.

C++SQLStorage EngineDatabase Systems

Mail Guard

mail-guard

A team IoT mailbox-monitoring prototype with ESP32-CAM firmware, a Next.js backend, image storage, and alert workflows.

Next.jsTypeScriptC++IoT