agentic-governance

The industry-standard Agentic Identity & Inventory Scanner. Automatically inventory autonomous agents (LangChain, AutoGen, CrewAI, PydanticAI) using static analysis, network heuristics, and eBPF. Foundational tool for AIBOM compliance and AgentOps governance.

Liminate is a prose-as-syntax language designed from the human end.

Python SDK for Permission Protocol — authority receipts for AI systems

Compliance-by-Design' scaffolding for AI-to-SMS interactions. Implements transient PII-scrubbing and age-appropriate content gating for COPPA 2026 & UNICEF-AI standards

LangGraph (Python) adapter for vsl-core: implements the VSLAdapter conformance contract and provides gated_node/route_on_denial to call a compiled gate before a StateGraph node runs and route around a denial. Ledger writes and Fallback retry logic stay in your own code — governance vocabulary lives in vsl-core. Alpha, MIT.

Governance and 2 human reviewer protocol for Agentic Hedgefund Workflows

Free, browser-based governance scan for any public repo — no account needed. A thin web wrapper (Express + React) around the X-Verba CLI engine: paste a GitHub URL, get a Gamma (Γ) score and governance report showing ungoverned decision points (AI calls, payments, DB writes, agent handovers). MIT licensed.

Local MCP proxy that governs what AI agents do on your machine. Policy enforcement, audit receipts, hash-chained provenance.

Help your AI agent author the Agreements that govern it.

Python HTTP client (RemoteLedgerStore) implementing vsl-core's LedgerStore Protocol against ledger-api, the hosted paid backend for VerbaLedger — so a ledger can write to a durable, multi-tenant store instead of a local file. Kept separate to keep vsl-core dependency-free. Alpha, MIT.

Verify what AI agents claim, not just what they're allowed to do. Semantic verification for the Liminate ecosystem.

Microsoft Agent Framework adapter for vsl-core: implements the VSLAdapter conformance contract and provides VSLFunctionMiddleware, gating every tool call an Agent makes before it fires. Ledger writes and Fallback retry logic stay in your own code — governance vocabulary lives in vsl-core. Alpha, MIT; real-Agent path not yet end-to-end tested.

LangGraph.js adapter for @supersemantics/vsl-core (TypeScript port of VSL-Core): implements the VSLAdapter conformance contract and provides gatedNode/routeOnDenial to gate a node before it runs and route around a denial. Ledger writes and Fallback/retry logic are not handled here — policy vocabulary stays in vsl-core. Alpha, MIT, not yet on npm.

This is a governed agentic workflow with HITL for 3rd Party Data Migration

Rankings-and-tiers decision support for fantasy football drafts. Public method, private source data.

AI Governance Platform (AIGP) for enterprise AI risk management — deterministic, pre-execution runtime enforcement producing signed, independently verifiable evidence for every AI decision. Guardrails, agentic AI security, model risk, EU AI Act / NIST AI RMF / ISO 42001.

"The Computable Governance Operating System & Specification Ecosystem. Transforms operational actions into traceable, graph-driven institutional memory governed by machine-executable policies.

Semantic Agent Discovery and Attribution Registry (SADAR(TM)) specification

TypeScript port of vsl-core: the same VSL governance vocabulary (PreNode, Invariant, AssuranceBasis, VerbaLedger, Cluster) for Node/TS agent frameworks, without a Python runtime. Framework-agnostic, zero runtime dependencies. Python vsl-core remains the reference implementation. Alpha, MIT, not yet on npm.

Permission Protocol Receipt Format (pp-receipt-v1): an open, signed authority receipt specification. Apache 2.0.