Auditability Python Packages

arbiter-engine

A detection engine that reports what it did not check. Eight axiom families over a domain model declared in YAML, with every declined evaluation recorded as a machine-readable reason.

hyodo

Local evidence verification for AI-assisted work. See what ran, what the evidence supports, and what remains unknown. HyoDo does not run or authorize agents.

atmem

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem

matrixai-core

MatrixAI: auditable AI models from prompts.

fcop-mcp

FCoP — file-based behavior-governance protocol for multi-agent AI. Tasks, reports, review, evidence, and lifecycle state over ordinary files; Python + MCP.

fcop

FCoP — file-based behavior-governance protocol for multi-agent AI. Tasks, reports, review, evidence, and lifecycle state over ordinary files; Python + MCP.

novafabric

Open-source replay and evidence infrastructure for AI agents. Capture runs as portable Run Capsules for replay, diff, lineage, provenance, and audit.

atmem-atbot

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem

verifier-standard

VSTD: portable, bounded, refutable evidence for computational claims and provenance graphs.

aetnamem

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem

arvis

A runtime assurance kernel for LLM-based systems: graded verdicts, hashed commitments, bit-identical replay.

openintent

A neutral protocol for coordinating intent across humans and agents. Goal lifecycle, state, auditability.

dbl-gateway

Reference implementation of the DBL execution boundary. Deterministic event chain separating intent, policy, and execution.

hrevn-mcp-server

Thin HREVN MCP server exposing baseline diagnostics, bundle tools, and audit-ready workflow integrity through the live managed runtime.

jhcontext

PAC-AI: Protocol for Auditable Context in AI — Python SDK

fortifyroot-ocelle

The core FortifyRoot LLMOps SDK for Python.

trace-stat

Lightweight execution logging for Python statistical programming.

evidence-sufficiency-calc

Python library for evidence sufficiency scoring in governance assessments under delayed ground truth, drift, and decision-readiness constraints.

openvibecoding-orchestrator

OpenVibeCoding is the command tower for AI engineering: plan, delegate, track, resume, and prove long-running work across Codex and Claude Code.

canon-gate

Policy-aware runtime governance for AI agents, automation, and controlled execution.

veramem-kernel

Minimal cognitive kernel for traceable reasoning, temporal integrity, and data sovereignty.

hrevn-anthropic-runner

HREVN for Claude Code: verifiable workflow state via MCP, skills, and a local runner.

reasoned-ops

Routes service requests, preserves machine/human decision history, records outcomes, and blocks unsupported management comparisons.

cortexpilot-orchestrator

OpenVibeCoding is the command tower for AI engineering: plan, delegate, track, resume, and prove long-running work across Codex and Claude Code.