#governance

Umbrella for the LLM Dark Patterns Hooks suite — single-purpose Claude Code Stop hooks that suppress sycophancy, paternalism, false-success, permission-loops, training-cutoff confidence at the textual boundary.

Sample queries and a Copilot agent skill for exploring your Power Platform inventory with pac admin query.

Client-side HTTPS egress proxy for TokenSaver — MITM capture for Claude Code / Cursor / agents.

Proof Gradient is the agent evolution protocol where every run leaves proof, every proof selects intelligence, and every selected artifact evolves the network.

A governance harness for Claude Code with blocking enforcement hooks, routed standards, and multi-project trackers with resume points. Free, MIT.

LORM — Layered Operational Responsibility Model: L0-L5 autonomy levels graded by authorization source, with a trust promotion/demotion lifecycle. Spec + Claude Code plugin (agent skill + policy-driven enforcement hooks).

A sanitised, clonable pattern for a personal AI operating system built on Claude. By a non-coding PM.

Adaptive AI software engineering workspace for Claude Code — lightweight by default, powerful when needed.

AI-agent reliability and governance layer: auto-firing compliance checks, persistent memory, security scanning, and verification loops that wrap any AI agent.

Capability Host Protocol — make agent and tool execution visible, replayable, and ready for governance.

Governed Agents (hackathon project). A governance infrastructure layer for multi-agent AI systems, built for the Band of Agents Hackathon on lablab.ai (Track 3: Regulated and High-Stakes Workflows). The product is not the agents themselves but the trust layer that makes agents deployable in regulated enterprise environments

Guardrails for AI coding agents. EADOS generates a governed repo - agent contract, ADRs, CI gates, SemVer - for any of 19 languages, then enforces the rules with lint. Works with Claude Code, Codex, and Gemini.

APXV Lab — air-gapped Bound Agents, Packs, Proofs, Pipelines & Swarms. Desktop installers (Windows + Linux). Local API. Fail-closed claims. Apache 2.0.

Versioned operating loops and portable capability Capsules for persistent agent work.

Enterprise AI-Native Trust & Safety Operating System powered by Multi-Agent AI for Explainable Investigations and Autonomous Risk Decisioning.

MCP server: check a folder of markdown against Open Knowledge Format (OKF) v0.2 and JidoSeal-defined Bronze/Silver/Gold frontmatter tiers (not ISO certification), locally, from Claude, Cursor, GitHub Copilot, Codex, Gemini CLI or a local model. Engine proprietary; no-egress is a vendor claim, see README.

Policy-as-code admission controller for AI agent skills and MCP tools. SkillBOM, lockfiles, and supply-chain baselines.

Protocol, governance, and validation framework for reliable AI-agent development.

Enterprise AI Platform — build, deploy, monitor and govern AI applications at scale (RAG, Agents, MLOps, LLMOps, Governance)

Turn Microsoft Copilot (Excel + Chat) into a disciplined, evidence-driven project operator. 43 skills, frozen acceptance criteria, deterministic lint gate, revision-controlled workbooks. No Cowork, no add-ons — built for strict corporate environments.

Source of agent-passport.org, the Agent Passport System website.

Loomio tools for Claude. Local install via npx, org-wide via Custom Connectors. Read-only mode supported.

A covenantal standard for bounded, answerable, revocable AI agents.

ZGPM-konformer Multi-Agent-Planner für AEGIRA — kompiliert portable Claude-Code-Harnesses (Phase-1-Spike).

Production-grade AI incident response system built on n8n. 3 workflows, human approval gate, dual-model fallback, and 23-column governance audit trail.

NOA — the Agent Action Receipt. Open governance layer for AI agents: gate risky actions before they run, emit a tamper-evident receipt anyone can verify offline. Early access · Apache-2.0.

A governance and policy layer that wraps Claude Code with review gates, audit trails, and plain-English rules for multi-agent engineering.

A seatbelt for the AI acting on your systems — deterministic, open-source governance gate for AI-agent actions

Open-source AI Agent + ADQA decision layer. Telegram, WhatsApp, X, Discord. BYOK. Hermes/OpenClaw compatible.

Switchback Governance · 折返治理 — the human-in-the-loop governance layer for multi-agent teams (GOAI 2026 Track 1)

Local-first AI agent & AIOps platform running fully offline on Tesla M40 (Maxwell CC 5.2). Single Docker/Unraid app with provider gate, RAG, MCP, workflows, AIOps, governance.

Agentic Contract-Governed Development (ACGD): contract-governed delivery for teams of AI coding agents — interface registries, role-scoped agent briefs, compliance gates and independent verification.

Governance pipeline for AI agent Git commits on Cloudflare Artifacts

A coding-discipline spec for OpenAI's Codex CLI, enforced by native Codex hooks + a rule-hit telemetry loop. Turns an AGENTS.md the model drifts from into a system that holds. Independent of oh-my-codex.

Turn documents, wikis, emails, and Confluence/SharePoint/OneDrive/Google Drive sources into governed, provenance-bearing knowledge AI agents can trust — reviewed publication, conflict retention, citation-exact retrieval. Native in Claude Code, Codex, Kiro, and any MCP client.

A tiny, production-shaped agent runtime: durable by default, gated by design, evaluated before it ships

BANXE repo template — CANON v1.0 controlled-copy baseline (.claude + factory-guard + claude.yml + guardian.yml)

One-click AWS agent that quarantines untagged resources before they become a threat