Ai Guardrails Python Packages

pydantic-ai-shields

Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction, tool permissions, and async guardrails. Built on pydantic-ai's native capabilities API.

soma-governance

Deterministic governance and guardrails for autonomous AI coding agents. Features AST verification, evidence-based rule execution, and native MCP support for Antigravity and Claude Code.

jev-judge-mcp

Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.

sourcerykit

Python SDK for accurate and verifiable agent tool use. Agents verify that answers came from the right source and were not changed. Downstream agents detect 100% of errors and retry to achieve a 50% jump in answer accuracy.

aiagentallowlist

AI Agent Allow List API client: page-type verdicts (allow, deny, flag) before an AI agent opens a URL

pydantic-ai-middleware

Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction, tool permissions, and async guardrails. Built on pydantic-ai's native capabilities API.

yagami

Self-hosted LLM gateway and AI context firewall for PII/PHI containment, prompt-injection defense, and governed agent tools.

cerbia-cli

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loaders, multi-layer de-obfuscation, specialized scanners, and automatic enforcement.

cerbia

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loaders, multi-layer de-obfuscation, specialized scanners, and automatic enforcement.

toolboundary

Local runtime security and policy enforcement for AI agents and LLM tool calls, with permissions, guardrails, rate limits, approvals, auditing, and an emergency kill switch.

cerbia-core

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loaders, multi-layer de-obfuscation, specialized scanners, and automatic enforcement.

cerbia-ml

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loaders, multi-layer de-obfuscation, specialized scanners, and automatic enforcement.

cerbia-protectai

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loaders, multi-layer de-obfuscation, specialized scanners, and automatic enforcement.

aetherlab

Official Python SDK for AetherLab - AI guardrails, LLM safety, and content moderation API

cerbia-presidio

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loaders, multi-layer de-obfuscation, specialized scanners, and automatic enforcement.

lelu-agent-auth-sdk

Open source authorization engine for AI agents. Confidence-aware gating · Human-in-the-loop review · Policy-as-code · Full audit trail

shekel

LLM budget control and cost governance for AI agents. Python library for token budgets, usage limits and guardrails for OpenAI, Anthropic, LangChain, LangGraph and agentic systems.

zerolabz-sentinel

Sub-millisecond stateless AI guardrail reverse proxy and inference security middleware. Intercepts prompt injections, jailbreaks, and credential leaks in <0.4ms.

ai2070-l0

L0: The Missing Reliability Substrate for AI. Streaming-first. Reliable. Replayable. Deterministic. Multimodal. Retries. Continuation. Fallbacks (provider & model). Consensus. Parallelization. Guardrails. Atomic event logs. Byte-for-byte replays.

scyvera

The missing governance layer for AI agents. Declare what your agent can do, what requires human approval, and what it can never do - before it runs. Runtime enforced via scyvera, not just documented.

openbias

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

opensentinel

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

ouro-loop

Give AI coding agents (Claude Code, Cursor, Aider, Codex) a structured autonomous loop with guardrails — boundaries, 5 verification gates, 3-layer self-reflection, and autonomous remediation. pip install ouro-loop. Zero dependencies.

reliable-ai-streams-py

L0: The Missing Reliability Substrate for AI. Streaming-first. Reliable. Replayable. Deterministic. Multimodal. Retries. Continuation. Fallbacks (provider & model). Consensus. Parallelization. Guardrails. Atomic event logs. Byte-for-byte replays.