The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

Auditable offline edge intelligence for low-cost edge devices, with benchmark evidence and public board proof on ESP32-C3.

A proactive AI agent for secure, traceable, human-in-the-loop task execution over long-running workflows.

I've always believed that the hardest problems in AI aren't technical; they're architectural. We keep building systems that can't explain themselves, can't prove their own integrity, can't handle uncertainty without either freezing or lying. And then we act surprised when we don't trust them.

paceval is a high-performance mathematical runtime for deterministic AI and energy-efficient edge computing.

Defensive preprint, governance, and threat model for DOORM Genmount WorldModel-OS — a governance-first architecture for auditable agentic reasoning.

L1 platform skeleton for DOORM WorldModel-OS — gateway, discrete-anchor state space, append-only audit trail, and four-level rollback contract for auditable agentic reasoning. Code release pending §11 gates.

GATOS generalizes Git’s content-addressed DAG into a complete computational substrate: a programmable operating surface unifying history, policy, and computation within a deterministic, verifiable feedback loop.

Outer-project research shell for the Vibe Science kernel.

Standardize AI agent behavior across IDEs and CLI tools using a single configuration file to reduce token usage and build persistent skill libraries.

The 2026 canonical record of Deterministic Intelligence — Scrollchain 0–167, DI² runtime architecture, and the complete provisional patent framework for drift-free, auditable AI.

Automate software evolution workflows and manage repository lifecycle tasks through a centralized platform.