Guardrails Cursor rules

20 tagged Guardrails, measured the same way as everything else here.

Browse within: AI Safety 11LLM 7gemini 6model-context-protocol 6enterprise-ai 5

RULE

01

NVIDIA-NeMo/Guardrails

Cursor rule Cursor

Referring to product names.

not rated 7.3k +35 yesterday A 50 tokens

akto-core-rules

02

akto-api-security/akto

Cursor rule Cursor

Akto is the fastest growing AI Security platform for your teams to secure AI agents, MCPs, LLMs, Agent skills, Gen AI apps in your organization.

not rated 1.5k +1 changed 1mo ago A 129 tokens original MIT

IgorGanapolsky/ThumbGate

Cursor rule Cursor

Deny a shell or network command that would print a secret or repeat a recorded lesson failure. Use before Bash, terminal, or HTTP tool calls.

not rated 29 +1 yesterday A 0 tokens original MIT

agentguard

05

bmdhodl/agent47

Cursor rule Cursor

AgentGuard local-first safety.

not rated 4 yesterday A 0 tokens original MIT

Jott2121/agent-gate

Cursor rule Cursor

Use when writing or changing README numbers, eval/benchmark code, experiment results, writeups, PR descriptions with metrics, or build-in-public post drafts.

not rated 3 2d ago A 0 tokens original MIT

security-guardrails

07

ofershap/vibe-guard

Cursor rule Cursor

Vibe Guard - always-on security guardrails for AI-generated code.

not rated 1 7mo ago A 282 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: