PHPackages ykachala/guardrails - PHPackages - PHPackages [Skip to content](#main-content)[PHPackages](/)[Directory](/)[Categories](/categories)[Trending](/trending)[Leaderboard](/leaderboard)[Changelog](/changelog)[Analyze](/analyze)[Collections](/collections)[Log in](/login)[Sign up](/register) 1. [Directory](/) 2. / 3. [Security](/categories/security) 4. / 5. ykachala/guardrails ActiveLibrary[Security](/categories/security) ykachala/guardrails =================== Input/output safety layer for PHP LLM apps: PII redaction, prompt-injection detection, secret scanning, and content moderation as a composable pipeline. 00PHP Since Jun 2Pushed 1mo agoCompare [ Source](https://github.com/ykachala/guardrails)[ Packagist](https://packagist.org/packages/ykachala/guardrails)[ RSS](/packages/ykachala-guardrails/feed)WikiDiscussions main Synced 1w ago READMEChangelogDependenciesVersions (1)Used By (0) Ykachala Guardrails =================== [](#ykachala-guardrails) > A composable input/output safety layer for PHP applications that call LLMs. Redact PII before it leaves your server, catch prompt-injection and jailbreak attempts, scan for leaked secrets, and moderate model output — all in one pipeline. [![PHP Version](https://camo.githubusercontent.com/5a2eb3f6217f798b7ca58d59764e8fd3d779752c0cef2b8634034d9e7e4ba92d/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7068702d253345253344382e332d373737626234)](https://www.php.net/)[![License](https://camo.githubusercontent.com/f8df3091bbe1149f398a5369b2c39e896766f9f6efba3477c63e9b4aa940ef14/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f6c6963656e73652d4d49542d677265656e)](LICENSE) --- Why this exists (the 2026 gap) ------------------------------ [](#why-this-exists-the-2026-gap) The PHP AI ecosystem grew up fast in early 2026 — **Prism PHP**, **Neuron AI**, and the official **Laravel AI SDK** now cover the *happy path*: making calls, RAG, agents, and structured output. What none of them own is the **safety boundary**. In the Python world this is a solved, well-funded problem: **LiteLLM** guardrails and **pydantic-ai-shields** ship PII filtering, prompt-injection defense, and secret redaction out of the box. PHP teams shipping AI to production in 2026 have **no native equivalent** — they either roll fragile regexes by hand or proxy everything through a Python sidecar. Ykachala Guardrails closes that gap with a framework-agnostic, provider-agnostic safety pipeline that sits between your app and *any* LLM client. What it does ------------ [](#what-it-does) GuardStageWhat it catches`PiiGuard`input + outputEmails, phones, SSNs, credit cards, IBANs, IPs — **reversibly tokenized** so you can restore them after the round-trip`InjectionGuard`input"Ignore previous instructions", role-override, delimiter-escape, and encoded jailbreak patterns (heuristic + optional LLM classifier)`SecretGuard`input + outputAPI keys, bearer tokens, private keys, `.env`-shaped values`ModerationGuard`outputToxicity, banned topics, configurable category thresholds`SchemaGuard`outputRejects responses that break an expected shape before they reach usersEach guard returns a **verdict** (`allow` / `redact` / `block`) with a reason, so you decide the policy: fail closed, fail open, or sanitize-and-continue. Install ------- [](#install) ``` composer require ykachala/guardrails ``` Quick start ----------- [](#quick-start) ``` use Ykachala\Guardrails\Pipeline; use Ykachala\Guardrails\Guard\PiiGuard; use Ykachala\Guardrails\Guard\InjectionGuard; use Ykachala\Guardrails\Guard\SecretGuard; $pipeline = Pipeline::make() ->input(new InjectionGuard(action: 'block')) ->input(new SecretGuard(action: 'block')) ->input(new PiiGuard(action: 'redact')) // reversible ->output(new PiiGuard(action: 'restore')); // put real values back // 1. Sanitize what you send to the model $safe = $pipeline->inbound($userMessage); if ($safe->blocked()) { throw new UnsafeInputException($safe->reason()); } $response = $yourLlmClient->chat($safe->text()); // 2. Sanitize what you show the user $clean = $pipeline->outbound($response, context: $safe); echo $clean->text(); ``` ### Reversible PII tokenization [](#reversible-pii-tokenization) ``` // "Email john@acme.com about order 4111-1111-1111-1111" $safe = $pipeline->inbound($text); // -> "Email about order " (sent to the model) $restored = $pipeline->outbound($modelReply, context: $safe); // model's "" placeholders are swapped back to john@acme.com ``` Framework bridges ----------------- [](#framework-bridges) - **Laravel** — `GuardrailsServiceProvider`, config publish, and a `guarded()` macro on the Prism/Laravel-AI pending request. - **Symfony** — a `GuardrailsBundle` with a tagged-service guard registry and middleware. - **Vanilla** — the `Pipeline` is pure PHP with zero framework deps. Architecture ------------ [](#architecture) ``` src/ ├── Pipeline.php # orchestrates inbound/outbound passes ├── Verdict.php # allow | redact | block + reason + redaction map ├── Guard/ │ ├── GuardInterface.php │ ├── PiiGuard.php │ ├── InjectionGuard.php │ ├── SecretGuard.php │ └── ModerationGuard.php ├── Detector/ # low-level detectors (regex + pluggable ML) └── Bridge/ # Laravel + Symfony integration ``` Roadmap ------- [](#roadmap) - Core pipeline + verdict model - Regex detector pack (PII, secrets) with locale-aware rules - Heuristic injection detector + optional LLM classifier adapter - Reversible tokenization store - Laravel & Symfony bridges - Pluggable model-based detectors (toxicity, semantic PII) See [`CLAUDE.md`](CLAUDE.md) for the full phase plan and conventions. License ------- [](#license) MIT ### Health Score 19 — LowBetter than 9% of packages Maintenance59 Moderate activity, may be stable Popularity0 Limited adoption so far Community6 Small or concentrated contributor base Maturity11 Early-stage or recently created project Bus Factor1 Top contributor holds 100% of commits — single point of failure How is this calculated?**Maintenance (25%)** — Last commit recency, latest release date, and issue-to-star ratio. Uses a 2-year decay window. **Popularity (30%)** — Total and monthly downloads, GitHub stars, and forks. Logarithmic scaling prevents top-heavy scores. **Community (15%)** — Contributors, dependents, forks, watchers, and maintainers. Measures real ecosystem engagement. **Maturity (30%)** — Project age, version count, PHP version support, and release stability. ### Community Maintainers ![](https://www.gravatar.com/avatar/5c5892a06b5cc3a1f6adaa3fa3d0cb5e9f77c6fc613425df614e2c4778b2e0a7?d=identicon)[joel767443](/maintainers/joel767443) --- Top Contributors [![ykachala](https://avatars.githubusercontent.com/u/985991?v=4)](https://github.com/ykachala "ykachala (6 commits)") --- Tags aianthropicguardrailslaravelllmmoderationopenaipiiprompt-injectionsecuritysymfony ### Embed Badge ![Health badge](/badges/ykachala-guardrails/health.svg) ``` [![Health](https://phpackages.com/badges/ykachala-guardrails/health.svg)](https://phpackages.com/packages/ykachala-guardrails) ``` ### Alternatives [mews/purifier Laravel 5/6/7/8/9/10 HtmlPurifier Package 2.0k18.7M144](/packages/mews-purifier)[paragonie/ecc PHP Elliptic Curve Cryptography library 24820.0k41](/packages/paragonie-ecc) PHPackages © 2026 [Directory](/)[Categories](/categories)[Trending](/trending)[Changelog](/changelog)[Analyze](/analyze)