Writing & Research

Published notes only. Drafts and private research stay outside the public site.

technical-note

Three-Stage Hybrid Search with Entity Routing

How to combine centroid search, parallel per-group HNSW queries, and entity routing into a recall-safe hybrid search pipeline.

Vector SearchChromaDBRetrievalArchitecture
technical-note

Sleep Mode: Agentic Memory Consolidation

Designing a consolidation pass that merges similar concept groups using both vector similarity and LLM-based contradiction analysis.

Agentic MemoryConsolidationLLMChromaDB
technical-note

Hierarchical Memory Retrieval with ChromaDB

How to structure persistent agent memory using concept groups and detailed cell retrieval in ChromaDB collections.

ChromaDBVector SearchAgentic Memory
technical-note

Building a Story Consistency Engine with Regex and Vector Search

Using regex-based fact extraction and vector-backed cross-referencing to detect contradictions in LLM-generated stories.

Agentic MemoryStory GenerationLLMPython
technical-note

Local Agentic Tools with Ollama Function Calling

How to wire local LLM function calling into a modular tool framework, and what I learned building six tools for NeuroSavant.

OllamaAgenticLLMTool Design
technical-note

Running a Vision LLM Locally for Real-Time Fitness Form Analysis

How the AI Fitness Trainer triggers Ollama + Qwen3-VL every 5 reps to deliver spoken form coaching — all on-device with no cloud dependencies.

OllamaQwen3-VLVision LLMPrivacyPython
technical-note

Canvas City Map Rendering with Procedural Roads and Assets

Building an interactive 14x9 tile map renderer in plain HTML5 Canvas — procedural road connections, 40+ sprite variants, deterministic props, and full pan/zoom/click interaction.

TypeScriptCanvasGame DevelopmentProcedural GenerationFrontend
technical-note

Preventing Flicker with Dual-Arm Hysteresis in Bicep Curl Tracking

How a ±20° hysteresis bias stabilizes rep counting when both arms are visible during alternating bicep curl sets.

HysteresisState MachinePose EstimationBicep CurlComputer Vision
technical-note

Building a Local Q-Learning Agent for Simulation AI

How I built a self-contained Q-learning policy engine for a city simulation — no cloud APIs, no GPUs, just numpy and a Q-table that fits on a Raspberry Pi.

PythonQ-LearningReinforcement LearningGame AISimulation
technical-note

What I learned training a 100M custom LLM

Key takeaways from training the Velora-100M transformer model from scratch, including data prep and learning loops.

LLMTrainingPyTorch
technical-note

Building a Local AI Fitness Coach with YOLOv11 and Ollama

Breaking down the keypoint extraction math, state machine rep counting, and local Vision LLM feedback loop behind a privacy-first fitness tracker.

YOLOv11OllamaPose EstimationComputer VisionPython
research-note

Real-Time Face Recognition via WebGPU

Deploying YOLOv8 face detection and EdgeFace embeddings directly to browser GPUs for zero-latency client-side inference.

WebGPUONNXComputer Vision