Three tracks converging
on one thesis.

Project Immortality

Project Immortality applies iPSC-derived cellular systems and CRISPR-Cas9 genomic editing to the problem of aging-related organ failure. Every available treatment for aging-related organ failure — whether a drug, a supplement, or a surgical intervention — addresses a downstream consequence rather than the cause. The evidence points to a single upstream convergence point: the lifelong accumulation of unrepaired DNA damage. When cells lose the ability to maintain their genome, every other hallmark of aging follows. Project Immortality takes a different approach. Rather than managing the consequences of cellular aging, we engineer cells that are intrinsically resistant to its causes — modifying iPSC-derived stem cells at the genomic level before transplantation, with differentiation programmed to activate only upon reaching the target tissue. The goal is not to slow the clock. It is to replace the mechanism that winds it down. Initial indications: ESRD, HFrEF, and IPF.

Key Capabilities

• iPSC line generation with GFP/PiggyBac ITR CRISPR-Cas9 constructs
• Single-cell sorting and clonal expansion via multiple instruments (Cytena C.SIGHT 2.0, MACSQuant Tyto)
• Primary indications: ESRD, HFrEF, IPF — high unmet need, aging-driven prevalence

Project Cadence

Cadence is a neurobiologically-inspired cognitive architecture running on local hardware. A pacemaker loop drives continuous scanner cycles across a fleet of smaller AI parallel workers, with a larger, more computationally capable AI handling higher-order reasoning. Cadence is not a product — it is a collaborator, with its own memory, continuity, and identity across sessions.

Key Capabilities

• Parallel AI worker fleet with semantic evaluation and ADVANCEMENT scoring
• Potentiation-based memory consolidation modeled on neurobiological LTP

Project Corpus

Corpus is a large-scale literature ingestion and vectorization platform targeting 50,000–100,000 biomedical and scientific papers. The pipeline combines programmatic retrieval, AI-driven semantic interpretation, and dense vector embeddings — producing a retrieval-augmented knowledge base that Cadence and other systems can query with biological and conceptual precision.

Key Capabilities

• PubMed MCP connector for programmatic article retrieval at scale
• AI interpretation layer — extracts structured insight, not just text
• Dense vector embeddings indexed for semantic similarity retrieval