Search Packages

llm-guard

The Security Toolkit for LLM Interactions

nemoguardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

garak

the LLM vulnerability scanner

giskard

🐢 Open-Source Evaluation & Testing library for LLM Agents

agent-bom

Open security scanner for AI supply chain and infrastructure: agents, MCP, containers, cloud, GPU, and runtime with blast-radius analysis.

mcpsafetywarden

MCP servers expose tools with no information about what they actually do at runtime. mcpsafetywarden sits between your agent and any MCP server, profiling tool behavior, blocking destructive calls, and running active security audits before you trust them in a workflow.

xsafeclaw

Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University

sunglasses

Sunglasses for AI agents. Protection layer + neighborhood watch.

axonflow

Official Python SDK for AxonFlow — runtime control, MCP policy enforcement, approvals, and audit trails for production AI

medusa-security

AI-first security scanner with 76 analyzers, 9,600+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo

q-uestionable-ai

Agentic AI Security Research

navi-sanitize

Deterministic input sanitization for untrusted text — invisible characters, homoglyphs, and encoding tricks, handled before your code sees them. Zero dependencies, no ML. Python 3.12+.

aig-guardian

🛡️ Open-source LLM security library for Python. Protect your AI apps from prompt injection, data leakage, and harmful outputs in 3 lines of code.

agentseal

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

projectair

Project AIR: forensic reconstruction and incident response for AI agents. Signed AgDR decision records, OWASP ASI01-ASI10 detection, signed forensic evidence exports.

crossfire-rules

Regex rule overlap analyzer for DLP, secret scanning, SAST, and IDS tools

agent-aegis

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.

shisad

Security-first AI agent daemon — the model proposes actions, the runtime decides what execute

humanbound-cli

DEPRECATED: renamed to 'humanbound'. This is the final release; no further updates will be published.

mcp-audit-scanner

Security scanner for MCP (Model Context Protocol) server configurations. Detects prompt injection, credential exposure, supply chain risks, and more.

ziran

自然 ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous tool chain compositions via knowledge graph analysis, detects execution-level side effects (not just text output), and runs multi-phase trust exploitation campaigns that model real attacker behaviour.

arc-sentry

Whitebox prompt injection detector for self-hosted open-weight LLMs. Deployment-specific behavioral monitor; calibrates on your traffic, detects drift from that baseline.

sovereign-shield

AI security framework: deterministic Immutable input filtering, adaptive rule learning, optional LLM veto verification. Zero dependencies. Works without an LLM. Patent Pending.

cyberscanai

AI Agent Tool for Penetration Testing and Network Forensics