Jesse Moses

gitvoyant. Temporal Code Intelligence platform. Time-series complexity analysis across Python, JavaScript, Java, and Go. Linear regression trend detection, cyclomatic complexity tracking, confidence scoring, and predictive decay forecasting.

ai-agents-reality-check. Benchmarking the gap between AI agent hype and architecture. Three agent archetypes, 73-point performance spread, stress testing, network resilience, and ensemble coordination analysis with statistical validation.

Cre4T3Tiv3.

agent-academy-labs. Experimental framework for multi-agent coordination and collaborative learning architectures. Research platform exploring agent-based learning systems, coordination protocols, and emergent behavior analysis. Progressive tutorials from reactive agents to AI-driven distributed systems.

llm-prompt-debugger. Developer-first UI for testing, tagging, and exporting LLM prompts. Next.js 14, multi-provider support (OpenAI, Claude, Ollama), JSON and Markdown export.

unsloth-llama3-alpaca-lora. Custom model training using modern architectures. 4-bit QLoRA fine-tuning pipeline for LLaMA 3 8B with production-grade optimization. Memory-efficient training on consumer GPUs. Published adapter on HuggingFace. From training pipeline to deployed model.

gocmitra. Git commit assistant written in Go. Pluggable LLM backend (OpenAI, Claude, Ollama), zero-dependency binary, cross-platform.

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

llmops-dashboard. Modular framework for composing and debugging complex prompt pipelines. Real-time telemetry visualization, custom LLM integration, and modular architecture. Dev-ready prompt engineering platform for AI engineers.

jetson-orin-matmul-analysis. CUDA matrix multiplication benchmarking on Jetson Orin Nano. Four implementations, three power modes, five matrix sizes. 99.5% mathematical validation. C++/CUDA and Python.