ai-audit

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.

Open Source Reliability Harness: Make your agents follow rules. One line of code to‎ ‎enforce, trace, and improve. ‎ ‎

Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, deterministic checks, built for CI.

An open-source Python library designed for developers to calculate fairness metrics and assess bias in machine learning models.

A Python package suite for generating evidence-grade audits of responsible, secure, and trustworthy AI systems.

Production operations framework for AI-powered SaaS. The architectural patterns, failure modes, and operational playbooks that determine whether your AI systems scale profitably or fail expensively.

The flight recorder for AI agents. Tamper-proof, ISO 42001 + HIPAA-compliant audit trails for everything AI agents do on your system. File changes + shell commands + PHI detection + agent identity.

Cryptographic receipts that prove an AI output was not altered. Offline verification in 21 lines, no server or account. Ed25519 + SHA-256, 128-byte Rust core, optional ML-DSA-65 post-quantum signatures. Python and Rust.

Executable Rego policies for AI compliance, each traceable to a named article or control: EU AI Act, UK pro-innovation principles and UK GDPR Arts 22A-22D, NIST AI RMF, PRA SS1/23, FCA Consumer Duty, ICAO/FAA/EASA aviation, FERPA, SRA/BSB legal practice. Per-article coverage matrices state what is implemented and what is not.

Cryptographic audit receipts for AI coding agents. Ed25519 + Merkle + RFC 3161 TSA. Supports Claude Code, Codex CLI & Cursor.

Mines corrections from your AI agent's chat logs to catch recurring drift and overclaiming before the next response ships. A cheap-to-expensive pre-flight gate — regex, then structured scoring, then a pressure probe — plus memory that carries past corrections into similar tasks. MIT, zero dependencies.

Responsible AI auditing for LLMs and SLMs

OpenAI Codex plugin for evidence-first code review, audits, fact checks, run contracts, and bounded subagent workflows.

🛡️ AI GitHub Action that audits Solidity, Rust, and Move smart contracts for security vulnerabilities using Gemini.

PolicyBind is an AI Policy-as-Code platform that enables organizations to govern AI usage through a unified model registry, real-time token-based access control, and automated compliance reporting for frameworks like the EU AI Act and NIST AI RMF.

Compliance-as-code for AI systems: evaluate AI apps against EU AI Act, NIST AI RMF, and OPA/Rego policies.

Append-only event kernel with Ed25519-signed Merkle checkpoints. Every AI action gets a verifiable receipt.

Cryptographically verifiable audit trail for AI systems — Ed25519 signed, hash-chained Decision Receipts with ISO 42001 / NIST AI RMF compliance. No blockchain, no SaaS.

The cognitive discipline your AI-assisted projects need. Framework + Rust CLI to externalize scope, decisions, and risks (Charters, AILOG, AIDEC, ADR) so AI agents stay coherent across many turns. ISO 42001 / EU AI Act / NIST AI RMF evidence as a side effect. EN/ES/zh-CN.

AION Scaffold — Intelligent tree-to-filesystem generator. Built by Sheldon K. Salmon, Advocatus Diaboli. Part of the AION Constitutional Stack. Free forever. No tracking.