Audit Trail Python Packages

vaara

Adaptive AI Agent Execution Layer — risk scoring, audit trails, regulatory compliance (EU AI Act Article 14)

asqav

Python SDK for AI agent governance - audit trails, policy enforcement, quantum-safe signatures. Works with LangChain, CrewAI, MCP.

grantex

grantex is the identity, authorization, and audit infrastructure for AI agents — the "OAuth moment" for the agentic internet. We provide a universal SDK and cloud service that lets any AI agent act on behalf of a human with scoped, revocable permissions, cryptographic identity, and an immutable audit trail. Developers integrate in minutes.

atlast-ecp

ATLAST Evidence Chain Protocol — trust infrastructure for AI Agents

kaos-agents

Agentic runtime for KAOS: Runner, SessionMemory (with reflexion lessons), 5 patterns (Chat/PlanExecute/Research/Findings/Router), 14 MCP tools, FastAPI REST API, audit-trail telemetry recorder.

treeship-sdk

Python SDK for Treeship - portable trust receipts for agent workflows

insa-its

Runtime Security for Multi-Agent AI — Website & Documentation

leashd

Safety-first agentic coding framework. Three-layer safety pipeline (sandbox, YAML policies, human-in-the-loop approval) for AI coding agents. Pluggable runtimes (Claude Code, Codex), autonomous task orchestrator, full audit trail.

regaudit-fhe

Depth-tracked regulatory audit primitives for future FHE-CKKS execution.

agent-aegis

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.

bemi-sqlalchemy

Automatic data change tracking for SQLAlchemy

aevum-core

Aevum — the sealed movement. Replay-first, policy-governed context kernel.

sovigl

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

sandcastle-ai

Describe what you want. Go home. Sandcastle ships it. 6 AI providers, EU data residency, smart failover, cost intelligence, 20 step types, 236 templates. European-built, open source. pip install sandcastle-ai

observr

Audit trail and causal attribution for AI agents — one line to instrument

tunc-clm

Append-only handoff format for multi-session AI threads. Linear write cost at depth, full audit lineage. Any AI family.

bemi-django

Automatic data change tracking for Django

atb-sdk

Python SDK for ATB (Agent Trace Bundle) — local-first AI audit trail

aevum-store-oxigraph

Aevum — Oxigraph GraphStore backend (small deployments).

aevum-llm

DEPRECATED — use aevum-agent instead.

aevum-server

Aevum HTTP API server — wraps the five functions for any consumer.

aevum-store-postgres

Aevum — PostgreSQL GraphStore + ConsentLedger backend (team deployments).

qp-vault

Governed knowledge store for autonomous organizations. Trust tiers, content-addressed storage, Merkle verification, knowledge lifecycle, air-gap native.

aevum-cli

Aevum -- command-line interface for operating Aevum nodes.