{"repo":"vstorm-co/pydantic-ai-shields","free":true,"listed":false,"github":"https://github.com/vstorm-co/pydantic-ai-shields","clone":"git clone https://github.com/vstorm-co/pydantic-ai-shields.git","description":"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.","language":"Python","stars":92,"topics":["ai-agents","ai-guardrails","ai-safety","anthropic","async","content-moderation","guardrails","input-validation","llm","openai"],"license":"MIT","category":"ai-agents","readme_excerpt":"Pydantic AI Shields Drop-in guardrails for your AI agents. Cost & budget caps, input / output / tool blocking, PII & secret redaction — for any Pydantic AI agent. Docs &middot; PyPI &middot; Install &middot; Ecosystem &middot; Deep Agents Cost &amp; budget caps &nbsp;&bull;&nbsp; Prompt-injection defense &nbsp;&bull;&nbsp; PII detection &nbsp;&bull;&nbsp; Secret redaction &nbsp;&bull;&nbsp; Tool permissions &nbsp;&bull;&nbsp; Async guardrails --- ### ⬆️ Upstreamed to pydantic-ai-harness Working together with the Pydantic team, we are moving this library's functionality into the official pydantic-ai-harness , where it lives as pydantic ai harness/guardrails . For new projects, use the harness — it is maintained by Pydantic alongside Pydantic AI itself. This repository stays on PyPI and keeps working for everyone already depending on it. Landed upstream This library In pydantic ai harness.guardrails PR --- --- --- InputGuard InputGuardrail #219, merged as #249 OutputGuard OutputGuardrail #219, merged as #249 ToolGuard ( blocked , require approval ) ToolGuardrail — a guard over the tool's arguments plus a result guard over what it returned; approval is the approve outcome #470 AsyncGuardrail(timing=\"concurrent\") InputGuardrail(parallel=True) #249 Upstream a guard returns a GuardrailResult rather than a bare bool , so besides allow and block it can replace the value (redaction), retry an output, or ask for approval on a tool call. In review This library Upstream PR --- --- --- Pr","default_branch":null,"files":null,"tree":[],"storefront":"/r/vstorm-co","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/vstorm-co/pydantic-ai-shields/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}