Guardrails Python Packages

presidio-analyzer

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

presidio-anonymizer

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

nemoguardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

baml-py

The programming language for agents

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.

presidio-image-redactor

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

presidio-structured

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

datafog

Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.

agent-hooks-sdk

Framework-neutral control contract for AI agents: eight interception points, three verdicts, and a conformance kit.

assurance-budget

Your AI agent says it's done. Assurance tells you what it didn't check.

agentlint

Guardrails for AI coding agents (Claude Code, Codex, Cursor, Gemini, …): blocks dangerous writes and commands before they run.

assurance

Your AI agent says it's done. Assurance tells you what it didn't check.

shad0wllm

System 0 for your LLM: learns the fixed-choice answers your LLM gives (intents, routing, moderation) and serves the repeats in microseconds from a small CPU table, at most 5% disagreement, certified. Zero-code proxy for the OpenAI Decisions API, System One and chat models.

assurance-cli

Your AI agent says it's done. Assurance tells you what it didn't check.

charter-ai

Agent tools you declare instead of implement.

squidbrake

Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.

cuga

CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

assurance-mcp

Your AI agent says it's done. Assurance tells you what it didn't check.

guardmeter

GuardMeter — benchmark, compare, and gate AI safety guards. pip install guardmeter

archkeel

Archkeel checks architecture boundaries and declared changes in AI-assisted code.

jevals

Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.

contexer

Contexer keeps the important engineering decisions behind your software current and available to every coding agent.

assurance-core

Your AI agent says it's done. Assurance tells you what it didn't check.

chock

Governance-as-code for AI coding agents: author a policy once, enforce it on every agent (Claude, Copilot, Cursor, Codex) via git hooks, CI, and native controls.