Agents, automation, working software.
Technical builds that solve real problems. Agent frameworks, pipeline automation, model integration — shipped, documented, and designed to last.
What we've shipped.
Each one started with a real problem. None of them are prototypes dressed up as products.
Multi-Agent Orchestration Framework
Modular agent framework for coordinating multiple LLM-powered agents across tasks. Built-in memory, structured tool use, and clean handoff between specialized agents. Designed for workflows that need more than a single prompt chain.
Voice-Driven AI Assistant Pipeline
End-to-end voice chatbot — speech-to-text, LLM reasoning, text-to-speech with low-latency streaming. Custom voice models, tool-calling, and real-time conversational flow that actually works in production.
Automated Workflow Engine
Calendar, email, CRM, and task management APIs unified into a single decision layer. Handles scheduling, follow-ups, data sync, and escalation without anyone touching a spreadsheet.
Drone Telemetry & Calibration System
Custom firmware interface and telemetry dashboard for DJI drone fleet management. Real-time sensor data visualization, automated pre-flight calibration checks, and flight log analysis.
Local LLM Deployment & Fine-Tuning Kit
Toolkit for deploying and fine-tuning open-source language models locally. Includes quantization pipelines, evaluation benchmarks, and a clean inference API for running models offline without cloud dependency.
Same principles. Every build.
Start with the actual problem. Understand what the system needs to do before choosing the stack. Most automation projects die because people build for capability instead of for the specific workflow that needs to work.
Ship modular. Every component replaceable, testable solo, designed to extend. No monoliths, no vendor lock-in, no hidden dependencies that collapse when one service changes its API.
Document everything. If someone can't pick up the build and understand it in under an hour, it's not done.