auditability

Governance standard and reference toolset for LLM-maintained knowledge corpora

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

Small local-first agent kernel: bounded tools, reversible edits, auditable runs. CLI + Web, Ollama + compatible APIs.

Deterministic telemetry & control plane for multi-agent AI systems. Atomic POSIX JSONL event bus, W3C/OpenTelemetry DAG reconstruction, and circular handoff guardrails.

AI agent execution governance: pre-effect authorization, single-use permissions, policy enforcement, and verifiable reconciliation.

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

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

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

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

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.

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🥷

Start at the bodies bearing the weight. Track where the weight goes. Build solutions that remove the weight and transfer it to something that can bear it or abolish the need for the weight to exist altogether.

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

Operational Ontology public reference: principles, D+L+A, governance, and write-back for stateful AI operations. No production implementation.

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem

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

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.

Intentional internet for the classroom. Private by design. Open by conviction.

Open-source replay and evidence infrastructure for AI agents. Capture runs as portable Run Capsules for replay, diff, lineage, provenance, and audit.

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.