projects
active research, experiments, and technical studies — frameworks for the curious mind.
RUNES protocol
a declarative framework for composable agentic behaviors — skill graphs, policy routing, and emergent task decomposition for persistent AI systems.
activeideonexus
an agentic research framework for managing AI/ML projects — tracking ideas with genealogy, designing sandboxed experiments, and monitoring the competitive landscape.
researchbrowser agent v2
next-generation autonomous browser automation with vision-language models, persistent session memory, and multi-step task planning.
activeedge inference lab
benchmarking and optimizing quantized LLMs on constrained hardware — Jetson Orin, Raspberry Pi, and custom FPGA accelerators.
researchsemantic memory engine
a study of embedding-based memory consolidation — how agents can extract durable knowledge from ephemeral interactions and build coherent world models.
archivedmulti-model arena
a systematic evaluation framework for comparing LLM outputs across accuracy, coherence, creative reasoning, and cost efficiency dimensions.