Audit Python Packages

django-easy-audit

Yet another Django audit log app, hopefully the simplest one.

audit-alembic

An Alembic plugin to keep records of upgrades and downgrades.

pyaud

The pyaud framework is designed for writing modular audits for Python packages

cloakllm

Python SDK — PII cloaking middleware for LLM calls (spaCy NER + regex + Ollama)

lynx-agent

Policy-gated, durable, audited execution for AI agent tool calls. Every action gets a five-verdict policy check, a crash-safe checkpoint, and a tamper-evident audit event — a library, not a server.

keel-verifier

Independent verifier for signed AI audit exports and Permit-spec evidence

solflow

Per-entry-point, navigable call-graph visualizations of Solidity repositories — for Web3 security auditors.

cloakllm-mcp

MCP server — CloakLLM tools for Claude Desktop and MCP clients

hardax

HARDAX - Hardening Audit eXaminer

sclite-core

Schema-backed contract layer for governed AI/security workflows: intent, policy decisions, approvals, execution receipts, evidence, and replayable audit traces.

zing-audit

LLM relay reality check — a CLI that audits whether an API relay actually serves the model it claims (货不对板检测)。

delego

Intent-bound action authorization for AI agents — deterministic, per-action approval a prompt injection can't re-point, with a signed, tamper-evident audit trail.

mcp-audits

Audit all locally configured MCP servers for permission risks, prompt injection threats, and schema drift

air-blackbox

Open-source EU AI Act compliance scanner. 51 checks across Articles 9-15. Drop-in trust layers for LangChain, CrewAI, AutoGen, OpenAI. Local-first, no data leaves your machine.

mcp-permission-audit

Audit all locally configured MCP servers for permission risks, prompt injection threats, and schema drift

knowing

Permanent code intelligence layer. Learns what matters, expires what changed, proves what existed. Content-addressed graph with Merkle proofs, 25 extractors, 23 MCP tools. Gets smarter with use.

acgs-lite

Constitutional governance infrastructure for AI agents — the missing safety layer between your LLM and production

a11y-moda

非官方 · 台灣 MODA 無障礙標章自評 CLI · WCAG A/AA/AAA · Freego 補完 · LLM/VLM 自動化

nautilus-rkm

Policy-first data broker for AI agents — one call plans, routes, enforces, attests, and audits every data access. Built on Fathom.

safecadence-netrisk

SafeCadence Network Risk — local-first infrastructure + identity policy platform. 45 adapters (40 infra + 5 identity), 22 controls, 16 multi-vendor translators, capability-based RBAC, AI policy intelligence, attack-path graph, KEV+EPSS-prioritized CVEs, cross-system drift detection. MIT, BYO-AI.

ai-skill-audit

Audit AI skill and role files for quality and trust. Catches prompt injection, secrets, and destructive commands before they reach your agent.

gavio

The open standard AI gateway — PII protection, audit, reliability & cost control as composable interceptors. Same API in Python, Java & JavaScript.

cloud-audit

Fast, opinionated AWS security scanner. Curated checks. Zero noise. Copy-paste fixes.

raucle-detect

raucle gives every AI agent action a cryptographic receipt: what it did, by whose authority, against which provably-enforced policy. Portable across frameworks and organisations — signed trust registry, agent passports, cross-org handshakes, compliance evidence packs.