“guardrails and AI safety”

Safety guardrails: runtime overrides for AI-safety plugin blocks, and per-language security review for python, javascript/typescript, and go.

Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox…

Configure the shared guard against catastrophic shell commands in local AI agents.

Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.

Cloudflare Workers MCP server: ai-guardrails

Local checks for sudo, systemd, sshd, ufw, and secret leaks before an agent applies them.

Python framework with input and output guards that detect LLM risks, plus structured output generation

Guards AI models, apps and agents against prompt injection, data leakage and harmful outputs.

Open-source Python library for adding programmable guardrails to LLM-based conversational applications

LLM Guardr41l

llm-guardr41l

Stop AI coding tools from making changes you didn't approve.

Sparkle Guardrails

thesparkle

AI code security and guardrails for Cursor, Claude, Windsurf, VS Code & more - ON EVERY PROMPT

AXME Code

AxmeAI

Persistent memory, decisions, and safety guardrails for Cursor, GitHub Copilot, Cline, Continue, Roo Code, Windsurf, and VS Code chat agents

AI customer experience agents for consumer commerce brands, covering support conversations and customer insight reports.

19 Cursor rule files from Fullive-AI/Anima: Architecture-Guardrails, Branch-And-Commit-Workflow, Change-Scope-Control, Changelog-And-Versioning-Discipline…