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.

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

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 experimental Application Object Model for helping LLM agents understand, reason about, and operate real apps.

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.

Open-source runtime for auditable multi-agent evaluation, starting with professional capital-market investment agents.

A governance layer for autonomous AI agents, proven on a life: 30+ scheduled agents made auditable, self-healing, and human-gated by single-writer field ownership. Architecture and patterns, no personal data.

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

AetnaMem is agent Memory delivers fully local long-term auditable, proof-ready memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies, it supports OpenClaw, install it via pip.

KnowMesh / 知络: local-first knowledge asset compiler for auditable RAG, traceable citations, and maintainable document intelligence.

MUFO (MoveTips Unified Functional Ontology) is a unified ontology and semantic-rule foundation for human function inference, state modeling, safety constraints, and the Human Function World Model.

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.

Outer-project research shell for the Vibe Science kernel.

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

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

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

Your AI prepares. You have the last say. Local-first finance review with durable rules and audit trails.