LLM Guard: Is It Still Maintained in 2026?
ArchivedLLM Guard is an open-source Guardrails / LLM Firewall tool from Protect AI (a Palo Alto Networks company) — MIT, written in Python, built for Security toolkit for LLM interactions — input/output scanners for prompt injection, PII, toxicity, jailbreaks, and data leakage. As of 2026-07-13, its repository status is "Archived". Stars and last-push date are pulled live from the GitHub API.
Repository snapshot
- 3,164
- GitHub stars
- 2026-07-08
- Last push
- —
- Latest release
- MIT
- License
- Python
- Language
- Archived
- Status
Repo: protectai/llm-guard · Security toolkit for LLM interactions — input/output scanners for prompt injection, PII, toxicity, jailbreaks, and data leakage · pulled live as of , refreshed weekly
What LLM Guard does
Security toolkit for LLM interactions — input/output scanners for prompt injection, PII, toxicity, jailbreaks, and data leakage Protect AI (a Palo Alto Networks company) maintains it under the MIT license. Commercial vendors covering the same ground are scored, cell by cell, in the OWASP LLM Top 10 coverage matrix.
Status note: LLM Guard is flagged "Archived". Check the repo before you build a pipeline on it. (IMPORTANT DEVIATION FROM BRIEF: brief assumed 'Active' by default, but GitHub confirms this repo was archived by the owner on 2026-07-09 (three days before verification date), i.e. it just became read-only. Protect AI was itself acquired by Palo Alto Networks (deal completed July 22, 2025), and llm-guard's archival appears to be a very recent consolidation move. Flagging this as a notable, easily-missed status change.)
Install & source
Repository: https://github.com/protectai/llm-guard
Frequently asked questions
Is LLM Guard still maintained in 2026?
As of 2026-07-12, LLM Guard's repository is flagged "Archived". Check the latest push date on GitHub before you rely on it.
What license is LLM Guard under?
LLM Guard runs under the MIT license, maintained by Protect AI (a Palo Alto Networks company).
What is LLM Guard used for?
Security toolkit for LLM interactions — input/output scanners for prompt injection, PII, toxicity, jailbreaks, and data leakage. It sits in the Guardrails / LLM Firewall category.