Ai Audit Python Packages

g8e

Verify, then execute.

8K 6 3

attestplane

Verifiable audit substrate for AI agents — EU AI Act Article 12 ready. Apache 2.0.

6K 2 2

lintlang

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.

4K 140 14

aegis-latent-sdk

Self-hosted evidence gateway for AI systems: fail-closed policy, WAF, egress controls, signed durable MMR proofs, and offline verification across LLM providers.

2K 18 4

hermes-rubric

Evidence-first LLM-as-judge scoring for AI artifacts — papers, PRs, prompts, cold emails: synthesizes a rubric, collects quoted-evidence citations, scores only against that evidence, and hedges on thin evidence. Every dimension ties to a file:line or quote, with reproducibility receipts. 7 backends.

1K 2 2

touchstone-dqi

An open-source AI evaluation tool that makes results easy to trust and verify. Every result includes its confidence range and sample size, and everything is saved in an evidence bundle that anyone can check offline.

1K 0 0

aegis-latent-core

Self-hosted evidence gateway for AI systems: fail-closed policy, WAF, egress controls, signed durable MMR proofs, and offline verification across LLM providers.

1K 18 4

ai-audit-trail

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

889 4 1

hermeneutic

Turn corrections from AI agent logs into guidance for similar tasks. Local memory with semantic retrieval, prompt-context hooks, and response checks.

818 9 1

zizkadb-mcp

Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support EU AI Act Article 12 record-keeping. Drift detection, MCP, Python & TypeScript SDKs. Self-host or cloud.

431 138 38

zizkadb-langchain

395 138 38

aicertify

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

351 5 4

zizkadb-crewai

338 138 38

agentdb-mcp

312 129 37

zizkadb-sdk

308 138 38

aiauditlog

Open-source, vendor-neutral toolkit for creating, storing, querying, and verifying privacy-aware, tamper-evident audit logs for AI models, agents, tools, policy decisions, human reviews, and workflow outcomes.

285 0 1

eticas-audit

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

248 20 2

zizkadb-livekit

245 138 38

attestroot

Append-only, hash-chained evidence log for AI agents — tamper-evident audit trail with RFC 6962 Merkle checkpoints and deterministic replay. Pure stdlib, zero dependencies.

183 0 0

agentdb-sdk

178 129 37

incident-ledger

Append-only, hash-chained evidence log for AI agents — tamper-evident audit trail with RFC 6962 Merkle checkpoints and deterministic replay. Pure stdlib, zero dependencies.

143 0 0

openbias

Open Source policy enforcement proxy: Make your agents follow rules.

141 143 6

opensentinel

Open Source policy enforcement proxy: Make your agents follow rules.

127 143 6

seatbelt

Responsible AI auditing for LLMs and SLMs

118 7 0