Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
Install
npx skills add davila7/claude-code-templates --skill llamaguardnpx skills add davila7/claude-code-templates --skill llamaguard -a claude-code -gnpx skills add davila7/claude-code-templates --skill llamaguard -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/safety-alignment-llamaguardgh skill install davila7/claude-code-templates llamaguardgit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/safety-alignment-llamaguard ~/.claude/skills/llamaguard # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/safety-alignment-llamaguard ~/.agents/skills/llamaguard # Codex, Cursor, Gemini CLI, Copilot, OpenCode