Audit Logging Python Packages

scoped-mcp

Per-agent scoped MCP tool proxy — credential isolation, resource scoping, and audit logging for AI agent deployments

agent-sudo-mcp

Authorization, delegation, provenance, and verifiable-audit engine for AI agents. MCP adapter published.

sylo-sdk

Sylo is an open-source Python SDK and cloud platform that adds production-grade reliability to your existing AI agent pipelines — checkpointing, permission enforcement, human approval gates, and immutable audit logging — without replacing the frameworks you already use.

postkit

Postgres-native identity, configuration, metering, and job queues.

d-safelogger

Zero-dependency, stdlib-compatible Python logger with append-only routing, integrity sidecars, and multiprocess delivery-state observability.

regulated-ai-governance

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

aegize

Infrastructure for autonomous AI agents: identity, policy, permissions, approval workflows, and audit.

bh-fastapi-audit

PHI-safe audit logging middleware for FastAPI healthcare APIs

agentlock

An adversarially benchmarked reference implementation for pre-action agent authorization. Framework-agnostic tool permissions, identity verification, scoped access control, and audit logging for any AI agent.

bh-audit-logger

Generic event emitter for bh-audit-schema implmentations

aigovkit

Vigil AI Governance SDK — one-line LLM call logging plus evals (LLM-as-judge, RAG metrics, drift)

mcpkernel

The Security Kernel for AI Agents — MCP/A2A gateway with policy enforcement, taint tracking, sandboxed execution, deterministic envelopes, and Sigstore audit. OWASP ASI 2026 compliant.

ragcompliance

Audit trail middleware for RAG pipelines in regulated industries

capiscio-mcp

Trust badges for MCP tool calls - RFC-006 & RFC-007 implementation

lokryn-mcp-log

Compliance-grade audit logging for MCP client operations (SOC2, HIPAA, PCI)

proxilion

A deterministic runtime security SDK for LLM applications that prevents prompt injection, data leakage, and rogue agent behavior using high-performance, auditable rule-based guards instead of probabilistic AI inference.

ea-agentgate

Enterprise-grade security gateway for AI agents with middleware, tracing, and auto-rollback

openparallax-channels

Python wrapper for the OpenParallax channels module

openparallax-sandbox

Python wrapper for the OpenParallax sandbox module

openparallax-memory

Python wrapper for the OpenParallax memory module

openparallax-audit

Python wrapper for the OpenParallax audit module

openparallax-shield

4-tier AI security pipeline for autonomous systems

certainlogic-guard

Deterministic AI verification middleware that catches hallucinations and cuts token costs.

lokryn-compliance-log

Protocol Buffers schema for compliance-grade audit logging. Built for SOC2, HIPAA, PCI. First-class support for AI/agent systems.