guardrail

Prevent Kubernetes misconfigurations from reaching production (again 😤 )! From code to cloud, Datree provides an E2E policy enforcement solution to run automatic checks for rule violations. See our docs: https://hub.datree.io

Principled code generation from OpenAPI specifications

Prevent TransactionTooLargeException crashes. For good. A modern Android framework for safely transporting large Serializable objects between components, without the crashes.

First-of-its-kind AI benchmark for evaluating the protection capabilities of large language model (LLM) guard systems (guardrails and safeguards)

This is the official code for the paper "Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation"

Awesome AWS service control policies (SCPs), Resource Control Policies (RCPs), and other organizational policies

Principled code generation from OpenAPI specifications

Extensible Go microkernel for LLM guardrails, quota enforcement and policy plugins.

A budget fuse for Claude Code: cap a session in tokens or dollars and halt runaway goals and loops. Auto-arms a $50 cap on goals.

Korean-Language Guardrail Evaluation Dataset for AI Agents

模式匹配自动注入 steering rules，不占系统上下文 - Inject rules when needed, without wasting context. Similar to oh-my-pi's "Time-traveling stream rules", but with a very simple and compact code implementation.

AI 安全护栏 — 智能体防护 · 内容安全 · 多模型代理 | 可部署为网关或终端 EDR

Terraform-Guardrail (TerraGuard) MCP is an open-source governance framework that enforces consistent, executable guardrails for Terraform across CI/CD pipelines—helping teams deliver secure, compliant infrastructure at scale without slowing down development.

Principled code generation from OpenAPI specifications

Example app of Akka-Http, Scala, Guardrail that implements the Todo Backend API

AEGIS DreamDojo Guard SDK — Runtime safety validation framework for embodied AI world models (NVIDIA DreamDojo / DiT pipelines)

Moved to karlkfi/claude-bouncer. Workspace-boundary shell permissions for Claude Code.

Moved to karlkfi/claude-bouncer. Branch-aware git permissions for Claude Code — auto-approve safe git/gh commands, pause at main and destructive ops.

Korean PII detection and masking for text and images in an air-gapped environment (Dockerized, CPU-only)

bridge.ai/ClaudeWatch: screen dangerous shell commands/scripts