$ ls ~/projects --sort=date

< Projects />

Building the future, one commit at a time. Here are some of my open-source projects and research work.

8 total
STATUS:
ALL ACTIVE WIP COMPLETED ARCHIVED
TYPE:
ALL Research (19) Tools (10) AI/ML (10) Systems (9) Blockchain (2)
// AI/ML
PUBLISHED ACTIVE
AI/ML

agenttrace

A non-invasive debugging framework for multi-agent LLM systems that reconstructs causal fault graphs from execution log…

['Python' 'FastAPI' 'D3.js' 'Causal Graphs' +1
EXPLORE()
// AI/ML
ACTIVE
AI/ML

GraphLLMRec

GNN + LLM hybrid recommendation with grokking detection using LightGCN/GraphSAGE and Qwen2.5-3B.

Python PyTorch DGL
EXPLORE()
// AI/ML
ACTIVE
AI/ML

Uni-Layer

30+ layer contribution metrics from 7 categories unified in one toolkit, with bridges for Torch-Pruning and PEFT LoRA r…

Python PyTorch scikit-learn
EXPLORE()
// AI/ML
ACTIVE
AI/ML

GoGameExplanation

CoNLL 2026 submission: Evidence-Based Dominance theorem proves evidence verification is theoretically optimal for elimi…

Python KataGo Stockfish DeBERTa-v3 +2
EXPLORE()
// AI/ML
ACTIVE
AI/ML

IntegriRef

Targeting JASIST/ACL: The first citation verification system that goes beyond existence checking to full semantic claim…

Python DeBERTa-v3 SciBERT ONNX +2
EXPLORE()
// AI/ML
ACTIVE
AI/ML

RecCache

ML-aware caching for recommendation systems: 45% cache hit rate, 85% latency reduction on hits, and under 3% NDCG degra…

Python PyTorch Redis online K-Means +1
EXPLORE()
// AI/ML
ACTIVE
AI/ML

DeltaCache

KV cache optimization achieving 10-16x faster warm latency vs vLLM, validated across 84 tests on TinyLlama, Mistral-7B,…

Python vLLM PyTorch Prefix Trie +1
EXPLORE()
// AI/ML
LIVE DEMO ACTIVE
AI/ML

TinyInfer-WASM

A Rust-to-WASM neural network inference engine running directly in the browser: MobileNetV2 in 45ms vs ONNX.js 120ms vs…

Rust WebAssembly SIMD React/TypeScript +3
EXPLORE()