Tiny JavaScript library for preconditions, postconditions and invariants, intended for use with Contractual.

This document describes the public protocol model for Index Network: the entities, state transitions, agent obligations, privacy boundaries, and discovery semantics that define interoperable participation in the network.

Deterministic, offline mapping of a signed MakerChecker audit bundle to named regulatory obligations (21 CFR Part 11, EU Annex 11, GAMP 5, HIPAA 164.312). Emits MET / NOT_EVIDENCED / NOT_APPLICABLE per clause with citing seqs.

Durable obligations and delivery truth for conversational agents.

GovernMy.ai MCP server — query AI governance obligations from Claude Desktop, Cursor, or any MCP-compatible client

EU AI Act & NIS2 compliance — classify AI systems, check NIS2 obligations, and draft compliance documentation

EU AI Act compliance MCP server for Claude Code / Cursor — classify, explain obligations, generate Article 50 disclosures. Offline by default.

Conformance test kit for the ggui protocol. Drives a behavioral fixture catalog against a live implementation over WebSocket, plus three pure-function catalogs (schema, registration, resolution) for the gadget obligations, and reports a scorecard-style pa

MCP server and structured reference for AI law: obligations, regulations, provisions, evidence, and enforcement deadlines across jurisdictions. The obligation-registry layer of the PAICE legal graph.

htop-style TUI dashboard for pi-threading multi-agent systems — live thread monitoring, obligations, and message flow. Supports local-fs, Redis, MongoDB, and HTTP backends.

The repository-installable agent skills live in [`skills/`](./skills/): `assurancespec-authoring` creates and refines deterministic proposals, while `assurancespec-work` executes reviewed obligations without acquiring admission, verification, completion,

Harness-agnostic coordination state, recovery, obligations, and plan lifecycle tools for AI agents

Frozen schema for the Aarmos Scoped Tool Invite (aarmos.invite/1) — a signed, offline-verifiable capability grant that encodes audience, scope (subset of the 8×8 Action×Resource matrix), obligations, and expiry. Verifiable with @avar-standard/verify.

MCP server and static dataset for the AI Incident Law public-record corpus: AI-related litigation, regulatory action, tribunal records, and review-queue matters. Anchored to EveryAILaw obligations for cross-graph queries.

GeraCompliance MCP server — classify AI systems under the EU AI Act, look up obligations and articles. Deterministic, offline, no auth. A Gera Systems product.

EU AI Act readiness toolkit — classify an AI system's risk tier, get the obligations that apply, and generate a conformity checklist + starter documentation. CLI + library. Informational, not legal advice.

SQLite3 bindings for Koru with phantom type obligations

EU AI Act compliance MCP server - risk classification with structured signals, article grounding, GPAI systemic risk, Art. 6(3) exception assessment, Annex III/IV resources, deadlines, obligations, penalties, and FAQ. By Lexbeam Software.

CLI for Lexius AI compliance platform — classify systems, check obligations, calculate penalties, run assessments

GovernMy.ai SDK — AI governance obligations, evidence tracking, and runtime compliance for Node.js codebases