CSV plaintext export for noy-db — decrypts records and formats as comma-separated values. Gated by the RFC #249 `assertCanExport('plaintext', …)` gate; writes an audit-ledger entry on every call. Part of the @noy-db/as-* portable-artefact family (plaintex

Deterministic trust layer for AI agents — a governance gateway for MCP tool calls (allow/block/review + tamper-evident hash-chained audit ledger). OWASP Agentic (ASI) Top 10 mapped coverage. No LLM, zero-dep.

Aegis Mesh SDK for Node.js — per-task correlation IDs that thread through every audit-ledger row your agent's HTTP calls produce.

Drop-in audit/compliance callback handlers for LangChain, LangGraph, CrewAI, AutoGen, Mastra, PydanticAI, and Microsoft Agent Framework. Streams events into the Ujex hash-chained audit ledger (IETF draft-sharif-agent-audit-trail-00). Resolves LangChain RF

Spend firewall + tamper-evident audit ledger for AI agents. Policy-gates any payment call with deterministic rules, signed consume-once mandates, and a hash-chained flight recorder. Never holds funds or keys to funds.

Validate AAR record entries and checkpoints and audit ledger hash-chain integrity

Content safety + governance for AI agents in one import. IBM Granite Guardian risk classification, NVIDIA NemoGuard content moderation, autonomous-send caps, and a tamper-evident audit ledger — over the three.ws Trust Layer.

Governance and audit layer for AI agents that move capital: canonical risk policy engine, CHP decision gate with HITL, and a signed append-only audit ledger.

Lightweight SDK for bridging base44 applications with Azure PostgreSQL Flexible Server. Includes HIPAA/GDPR compliant audit ledger with field-level hash deltas.

Reference OpenAI Chat Completions integration for the `adjudicate` decision kernel. A thin shim over `@adjudicate/adapter-core` — every load-bearing concern (tool-use loop, defer/confirm orchestration, audit + ledger wiring, REWRITE handling, confirmation

Countersign SDK — the typed client agents and operators use to wire in the cross-vendor freeze, spend-guard, and live audit ledger. Browser + Node.

VasperaMesh CLI — authenticate from your terminal and wire your AI agents into the tamper-evident audit ledger.

Ledger Hardware Wallet Cardano ADA API

TypeScript SDK for the Hashline agent audit ledger.

Zero-dependency BPMN domain engine: model, lifecycle governance, validation, structured diff, hash-chained audit ledger, geometry and BPMN 2.0 XML (with DI).

Cots.ai agent interceptor SDK — configure once, then every governed action is intercepted, evaluated, held for approval if needed, and proven in the audit ledger.

<!-- @TODO -->

Action ledger schema, append-only write helpers, and idempotency primitives for Voyant control surfaces.

Ledger devices

Reference Vercel AI SDK (v5+) integration for the `adjudicate` decision kernel. A thin shim over `@adjudicate/adapter-core` — every load-bearing concern (tool-use loop, defer/confirm orchestration, audit + ledger wiring, REWRITE handling, confirmation-blo