Policy Enforcement Python Packages

assay-it

Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enforce egress in the kernel (eBPF/LSM, Linux). Deterministic, offline-first, bounded claims.

asqav

Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, audit trails. Works with LangChain, CrewAI, MCP.

arbiter-client

Arbiter: A capability firewall between AI agents and services

frontier-scout

Policy compiler + PR scope verifier for AI coding agents

policy

A Policy library provides support for RBAC policy enforcement.

comply54

African AI governance — runtime compliance enforcement for AI agents operating under NDPA, CBN, NIMC Act 2026, KDPA, POPIA and 15+ African regulations. LangGraph, CrewAI, and AutoGen adapters included.

release-gate

🚪 Governance gate for AI agents. Enforce policies before deployment: request contracts, operational safeguards, identity boundaries, action budgets. CLI tool with YAML config, JSON/text output, CI/CD integration.

arbiter-server

Arbiter: A capability firewall between AI agents and services

arbiter-imap

Arbiter: A capability firewall between AI agents and services

arbiter-smtp

Arbiter: A capability firewall between AI agents and services

arbiter-suite

Arbiter: A capability firewall between AI agents and services

execlave-sdk

Official Python SDK for Execlave — the AI Agent Management Platform (AMP). Tracing, runtime policy enforcement, and compliance audit trails for AI agents.

moralstack

MoralStack is a governance and safety layer for LLM applications. It analyzes user requests before generation, evaluates risk and intent, and decides whether the AI should answer normally, answer safely, or refuse. The goal is to make AI systems more auditable, controllable, and reliable in sensitive or regulated contexts.

arbiter-skill

Arbiter: A capability firewall between AI agents and services

varden

A self-hosted runtime firewall for AI agents

regulated-ai-governance

Comprehensive governance framework for AI agents operating in FERPA, HIPAA, GDPR, GLBA, ISO 42001, and 10+ regulated environments

dbl-gateway

Reference implementation of the DBL execution boundary. Deterministic event chain separating intent, policy, and execution.

drako

AI agent security and governance platform for the full lifecycle. Scan before you ship. Govern and block at runtime. No Azure required.

rulegraph

Declarative rule graphs for AI agent policy and constraint enforcement

sovigl

SOVIGL — AI agent payment governance SDK. Returns approved, pending, or blocked.

ai-agent-governance

The complete AI agent governance stack - kernel, trust mesh, runtime supervisor, and reliability engineering

baracuda

Runtime policy enforcement for AI tool calls. Define a YAML policy and intercept every MCP or LLM tool call before it executes.

janus-guard

System-level security for LLM agents: fine-grained policy enforcement on tool calls to defend against indirect prompt injection

arbiter-core

Core policy-controlled MCP gateway for agent-accessible services