// Guard secrets & permissions
llm-guardv0.3.16
The Security Toolkit for LLM Interactions
Open source Archived For agents
IN ONE PARAGRAPH
llm-guard is the Security Toolkit for LLM Interactions.
Good for: Developers who want their agent (Claude Code, Codex, Cursor…) to guard secrets & permissions.
Not for: anything that needs long-term maintenance (the project is archived).
01How to start
- 1Read the official README for requirements and permissions.
- 2Install it as the official guide describes.
- 3Tell your agent the command exists (e.g. in AGENTS.md / CLAUDE.md) so it knows when to call it.
02Alternatives & comparison
Compare side by side → garak the LLM vulnerability scanner ★ 9.6k guardrails-ai/guardrails Adding guardrails to large language models. ★ 7.6k NVIDIA-NeMo/Guardrails NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. ★ 7.3k casdoor An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD ★ 15k strix Open-source AI penetration testing tool to find and fix your app’s vulnerabilities. ★ 71k
03Related
- ›BlueDot Impact AI Alignment 课程 · BlueDot ImpactEnglish
- ›BlueDot Impact AI Governance 课程 · BlueDot ImpactEnglish
- ›AI Safety, Ethics and Society 教材 · Center for AI Safety / Dan HendrycksEnglish
- ›OWASP Top 10 for LLM Applications · OWASP GenAI Security ProjectMultilingual (incl. EN/ZH)
- ›MITRE ATLAS · MITREEnglish
- All tutorials →
Versions, why it is listed, for AI to read
For AI agents
- Interfaces：SDK
- Machine-readable record：/api/v1/software/llm-guard.json · llms.txt
- Added 2026-10-10 · updated 2026-10-22