Agent Governance Python Packages

vaara

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

haxaml

Git-style project memory and workflow governance for AI coding agents.

axonflow

Official Python SDK for AxonFlow — runtime control, MCP policy enforcement, approvals, and audit trails for production AI

haxaml-mcp

Git-style project memory and workflow governance for AI coding agents.

actra

Actra - control what runs before it runs, controls what actions are allowed before they execute. Evaluate policies across APIs, workflows and AI agents in real time.

langchain-runcycles

LangChain agent middleware for Cycles — pre-tool-call authorization and per-tenant budget enforcement for Python agents using create_agent

agents-shipgate

Static release-readiness gate for AI agent tool surfaces. CLI + GitHub Action. Scans MCP, OpenAPI, OpenAI Agents SDK, Anthropic, Google ADK, LangChain, CrewAI. Apache-2.0.

haxaml-ui

Git-style project memory and workflow governance for AI coding agents.

execlave-sdk

Official Python SDK for the Execlave AI Governance Platform — tracing, policy enforcement, and framework auto-instrumentation for LangChain, OpenAI Agents SDK, and CrewAI

dashclaw

🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.

runcycles

Python SDK for Cycles — reserve, commit, release budget and risk for AI agents

edictum

Runtime safety for AI agents. Stop agents before they break things.

traccia

Production-ready distributed tracing SDK for AI agents and LLM applications

constitutional-agent

WHY-layer constitutional governance for autonomous AI agents

runcycles-ap2

Cycles runtime authority guard for Google AP2 (Agent Payments Protocol) — reserve, commit, release around AP2 payment mandates to prevent mandate reuse, double-spend, and concurrent checkout attempts.

agentlock

The Open Authorization Standard for AI Agents. Framework-agnostic tool permissions, identity verification, scoped access control, and audit logging for any AI agent.

doctrine-agents

Code-like DSL and compiler for agent workflows that compile to portable AGENTS.md instructions.

agent-immune

Adaptive threat intelligence for AI agent security — semantic memory, multi-turn escalation, output scanning, rate limiting, and prompt hardening.

cloister

Graph-native agent harness and substrate for knowledge, memory, workflow, and MCP tooling

runcycles-openai-agents

Runtime budget, action, and audit authority for the OpenAI Agents SDK — enforce LLM cost limits, tool call caps, and audit trails before execution.

guardian-angel

Policy engine for governing AI agent tool execution.

rally-agents

Filesystem-first agent harness for strong, stable coding-agent workflows with repo-local run state.

onceonly-sdk

Execution safety & governance layer for AI agents: idempotency, budgets, tool control, audit logs.

csc-runner

Reference runner for Command Scope Contract