LLM Guard
OSS guardrails toolkit by Protect AI
About
MIT-licensed Python toolkit for LLM input/output filtering — prompt-injection detection, PII redaction, toxicity, anonymisation, bias, and more. Top OSS choice for self-hosted runtime guardrails in 2026.
Choose LLM Guard when…
- •You need OSS, self-hosted guardrails you can audit
- •You want a pluggable validator chain over your own LLM calls
- •You cannot send prompts to a managed third-party guardrails service
Builder Slot
Input/output validation, topic controls, and safety rails that ensure LLM responses stay within defined policies
Other tools in this slot:
Stack Genome Detection
AIchitect's Genome scanner detects LLM Guard in your project via these signals:
llm-guardIntegrates with (1)
Alternatives to consider (2)
Pricing
Pulse
● No incidents in the last 90 days
Recent Activity
Repository archived on GitHub
13 days ago
Health ↓ 55 → 0
13 days ago
Health ↑ 40 → 55
5 weeks ago
Crossed 1,000 stars ⭐
2 months ago
Went stale — 151d without a commit
2 months ago
Badge
Add to your GitHub README
[](https://www.aichitect.dev/tool/llm-guard)Explore the full AI landscape
See how LLM Guard fits into the bigger picture — browse all 207 tools and their relationships.