Product / UX / Safety & Guardrails

LLM Guard

An open security toolkit for LLM interactions from Protect AI, providing input and output scanners for prompt-injection, PII/data-leakage, toxicity, and harmful-content detection and sanitization. Self-hostable as a Python library.

LLM Guard, MIT, Python; ~3.1K GitHub stars (June 2026). Maintained by Protect AI (acquired by Palo Alto Networks). Verified live June 2026.

Openness

5 high confidence

5.0

license: MIT(OSI)
source: public(full Python implementation)
self-host: yes
service: none(the OSS toolkit
core-gated: ungated

Fully open source: MIT-licensed, complete source, self-hostable. (Protect AI's commercial platform is a separate product; this is the standalone OSS toolkit.)

https://github.com/protectai/llm-guard recorded 2026-06-29
MIT; full Python source; input/output scanners; ~3.1k stars

Adoption

2 low confidence

2.0

~3.1K GitHub stars (June 2026); stars-only proxy, capped per methodology.

https://github.com/protectai/llm-guard recorded 2026-06-29
~3.1k stars (June 2026)

Capability

3 medium confidence

3.0

Solid set of I/O scanners; lighter-weight orchestration than NeMo Guardrails but easy to drop in.

https://github.com/protectai/llm-guard recorded 2026-06-29
input/output scanners: injection, PII, toxicity, harmful content

Unchanged since 2026-08-01 (last edited, not re-checked)