$ ls ~/projects --sort=date

< Projects />

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

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

AgentMesh-STM

The largest empirical study of MARL coordination strategies applied to LLM multi-agent systems: 3,400+ episodes across …

['Python' 'OpenAI API' 'Ollama' 'MARL Algorithms (VDN/CommNet/QMIX/COMA)' +1
EXPLORE()
// Research
PUBLISHED ACTIVE
Research

Universe-Routing

A 465M-parameter fine-tuned router that classifies queries into 7 distinct epistemic universes (frequentist, Bayesian, …

['Python' 'Qwen-1.5-0.5B' 'HuggingFace Transformers' 'Fisher Information' +1
EXPLORE()
// Research
ACTIVE
Research

merkle-GPT

Applying cryptographic Merkle trees to LLM weight management: 520-823 MB/s build speed, 0.42% storage overhead, 50-68% …

Python PyTorch SHA-256 SQLite +2
EXPLORE()
// Research
ACTIVE
Research

encRec

Trie-routed recommendation under encrypted features for privacy-preserving ML

Python PyTorch DeepFM DLRM +1
EXPLORE()
// Research
ACTIVE
Research

LinkerLLM

Multi-model LLM serving system with weight section sharing inspired by runtime linkers

Python PyTorch CUDA Transformers
EXPLORE()
// Research
ACTIVE
Research

nanoZkinference

A zero-knowledge proof system for verifiable LLM inference using Halo2 IPA: 6.9KB proof per layer (O(1) size), 22ms ver…

['Python' 'Rust (Halo2 PyO3)' 'GPT-2' +3
EXPLORE()
// Research
ACTIVE
Research

Belief-Dynamics

Proving that standard multi-agent LLM consensus is mathematically broken under adversarial conditions, and proposing Or…

Python Ollama Cloud API TruthfulQA GSM8K +2
EXPLORE()
// Research
ACTIVE
Research

FisherKD-Unified

Fisher Information-guided adaptive knowledge distillation framework implementing 12+ distillation methods

Python PyTorch Transformers WandB
EXPLORE()