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

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

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

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.

An accountability layer for investment agents: thesis cards, prediction ledgers, stock screeners, and feedback loops.

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

Toward controlled evolution of artificial intelligence through validated neural grafting.

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.

ECHO-PPI: Evidence-bundled, auditable overlapping protein-module detection in protein-protein interaction networks.

Code and lightweight audit artifacts for auditable repair of scientific reasoning graph extraction on a 350-row benchmark.

A self-distilling neuro-symbolic cascade that amortises LLM cost across knowledge-graph QA and regulatory-compliance checking, with auditable Datalog proof trees.

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.

Defensive design pattern for high-stakes multi-agent LLM workflows. Typed evidence, deterministic adjudication, append-only receipts. Inventor: Simon Foster. CC0.

Bank Shield: Auditable AI for credit scoring that maintains accuracy while enforcing regulatory compliance (66% fewer breaches), proving resistant to adversarial text manipulation.

Local-first memory and simulation infrastructure for auditable AI agents. Index evidence, build knowledge graphs, run bounded simulations, and produce reviewable verdicts on local disk.

A verifier-anchored self-distilling neuro-symbolic cascade: a cheap, teacher-independent correctness verifier gates and corrects a frontier LLM before its answers distil into auditable, type-checked Datalog rules with proof trees.

Open-source memory and experience layer for persistent AI agents, with auditable decisions, evidence-based learning, and evolving identity.

Outer-project research shell for the Vibe Science kernel.

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