First Principles Framework (FPF): Operating system for open-ended thought for engieering, research, and mixed human/AI teams: bounded contexts, auditable reasoning, decision records, and multi-view publication.

OpenVibeCoding is the command tower for AI engineering: plan, delegate, track, resume, and prove long-running work across Codex and Claude Code.

Experimental OpenCode-first orchestration plugin inspired by the Tang Dynasty's Three Departments and Six Ministries: draft, review, dispatch, execute, and audit.

Proof of Human Intent (PoHI) - Cryptographically verifiable human approval for AI-driven development

A long-form article and practical framework for designing machine learning systems that warn instead of decide. Covers regimes vs decimals, levers over labels, reversible alerts, anti-coercion UI patterns, auditability, and the “Warning Card” template, so ML preserves human agency while staying useful under uncertainty.

Sifaka is an open-source framework that adds reflection and reliability to large language model (LLM) applications.

The first open-source implementation blueprint for Intelligent AI Delegation. A deterministic runtime (DIR) and architecture for Responsibility-Oriented Agents (ROA) to bridge the gap between LLM reasoning and safe, auditable production execution.

Umbrella repo for the ToxMCP Suite (docs, links, quickstart).

Lean orchestration platform for enterprise AI — where each decision costs hundreds. State machine core, HITL as a first-class state, corrections that accumulate. First use-case being Coding agent. Open research, early stage.

ADOS Turn AI into a repeatable, auditable SDLC: ticket → spec → plan → PR → quality gates → release. Agents, templates, skills, scripts, and reference workflows.

Kita is a grammar for language models that audits words as containers. It asks: who benefits, who pays, which way cost and benefit are flowing, and who decided the words to describe it. And starts at the cost-bearers.

This project integrates Hyperledger Fabric with machine learning to enhance transparency and trust in data-driven workflows. It outlines a blockchain-based strategy for data traceability, model auditability, and secure ML deployment across consortium networks.

Stop Claude Code from doing irreversible damage. Policy-gated execution + receipts so you can ship agents without sweating production.

Multi-Agents VSCode Extension that Focuses on the Full Control of Context, Observability and Auditability. Works like Wakaba Mutsumi's Personalilties 🥒. 吓我一跳我释放忍术😰若叶睦那么多首啊🥷

Governance layer for human–AI collaboration: evidence boundaries, audit artifacts, and change admissibility.

Determinism: Bit-identical outputs under identical inputs, configuration, and execution environment.

Auditable transparency pack for OddsFlow: verification rules, schemas, sample logs, and versioned notes (not betting tips).

SMALL (Schema, Manifest, Artifact, Lineage, Lifecycle) is a formal execution state protocol that makes AI-assisted work legible, deterministic, and resumable by separating durable state from ephemeral execution.

Governance beneath the model. Custody before trust. Open for audit. Constitutional Grammar for Multi-Model AI Federations, Firmware Specification • Zero-Touch Alignment • Public Release v1.0

Methodology defining structured workflow topology and reproducibility guarantees for governed research.