PyPI · npm
NVIDIA-NeMo/Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Custom licenseSep 17, 2026 · metrics 2.10.0
All tags
Catalogue tag
#llm-security
Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.
88 records
PyPI
Giskard-AI/giskard-oss
🐢 Open-Source Evaluation & Testing library for LLM Agents
Apache-2.0Aug 28, 2026 · metrics 2.10.0
PyPI · npm
NVIDIA/garak
the LLM vulnerability scanner
Apache-2.0Oct 19, 2026 · metrics 2.10.0
PyPI · npm
NuGuardAI/nuguard
AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.
Custom licenseSep 10, 2026 · metrics 2.10.0
npm
arcjet/arcjet-js
Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code.
Apache-2.0Sep 11, 2026 · metrics 2.10.0
Go · npm
beelzebub-labs/beelzebub
A secure low code deception runtime framework, leveraging AI for System Virtualization.
GPL-3.0Oct 19, 2026 · metrics 2.10.0
PyPI
cisco-ai-defense/skill-scanner
Security Scanner for Agent Skills
Custom licenseSep 17, 2026 · metrics 2.10.0
PyPI · npm
koda-ai-studio/agent-bom
Open security scanner and self-hosted control plane for AI, MCP, and cloud. One evidence model — run scans in your environment, centralize findings, govern in your VPC.
Apache-2.0Oct 16, 2026 · metrics 2.10.0
PyPI · npm
msaad00/agent-bom
Open security scanner and self-hosted control plane for AI, MCP, and cloud. One evidence model — run scans in your environment, centralize findings, govern in your VPC.
Apache-2.0Sep 8, 2026 · metrics 2.10.0
crates.io
nolabs-ai/nono
secure multiplexed execution paths for agents - zero trust, zero setup, zero latency.
Apache-2.0Sep 11, 2026 · metrics 2.10.0
Go
praetorian-inc/julius
Simple LLM service identification - translate IP:Port to Ollama, vLLM, LiteLLM, or 60+ other AI services in seconds
Apache-2.0Sep 17, 2026 · metrics 2.10.0
Go
Mindburn-Labs/helm-ai-kernel
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
Apache-2.0Sep 10, 2026 · metrics 2.10.0
npm
CyberStrikeus/CyberStrike
Open-source AI-powered offensive security harness for automated penetration testing.
AGPL-3.0Sep 13, 2026 · metrics 2.10.0
PyPI
usestrix/strix
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
Apache-2.0Sep 16, 2026 · metrics 2.10.0
PyPI · RubyGems
OWASP/www-project-agent-memory-guard
OWASP Foundation web repository
Apache-2.0Aug 25, 2026 · metrics 2.10.0
npm
asamassekou10/ship-safe
The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic core, no API key needed, JSON and SARIF output.
MITOct 22, 2026 · metrics 2.10.0
PyPI
DataFog/datafog-python
Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.
MITSep 9, 2026 · metrics 2.10.0
PyPI
mcp-hangar/mcp-hangar
MCP policy enforcement plane — deterministic policy on every Model Context Protocol call: identity, RFC 8707 audience binding, tool schema digest pinning, full audit trail. Python, self-hosted, MIT.
MITSep 21, 2026 · metrics 2.10.0
npm
node9-ai/node9-proxy
The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.
Apache-2.0Sep 13, 2026 · metrics 2.10.0
Go
Nox-HQ/nox
Open-source security scanner with first-class AI app security (prompt injection, embedding leakage, agent over-privilege, MCP hardening). Polyglot AIBOM, SARIF, SBOM. Cosign-signed plugin marketplace. Offline-first, agent-native via MCP.
Apache-2.0Sep 13, 2026 · metrics 2.10.0
PyPI
vaaraio/vaara
Accountable Autonomy: open-source evidence layer that gates every AI agent tool call against your policy and writes a hash-chained record an auditor verifies offline, without trusting you. Root-agnostic; binds to TPM 2.0 / SEV-SNP when present. Your environment, no SaaS, no telemetry. AGPL-3.0.
AGPL-3.0Oct 20, 2026 · metrics 2.10.0
npm · PyPI
Agent-Threat-Rule/agent-threat-rules
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable rules across 10 categories; merged into Microsoft AGT, Cisco AI Defense, MISP, OWASP, FINOS & SigmaHQ. MIT-licensed.
MITSep 9, 2026 · metrics 2.10.0
Go
airomhq/airom
Open-source AI Bill of Materials (AIBOM) scanner: inventories AI models, datasets, prompts, embeddings, vector DBs & RAG pipelines across code, containers & Kubernetes — with file:line evidence, load-time risk detection (poisoned pickle / Keras Lambda / unsafe torch.load) and NIST AI RMF / OWASP compliance mapping. CycloneDX · SARIF · JSON.
Apache-2.0Sep 13, 2026 · metrics 2.10.0
PyPI
sattyamjjain/agent-airlock
A type-checker and contract layer for AI agent tool calls, deny-by-default, in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.
Apache-2.0Sep 18, 2026 · metrics 2.10.0
Go · PyPI
adithyan-ak/AgentHound
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.
Apache-2.0Oct 20, 2026 · metrics 2.10.0
npm · PyPI
issdandavis/SCBE-AETHERMOORE
Geometric AI governance and evaluation framework with a 14-layer security pipeline, semantic projection, and reproducible benchmark lanes.
MITAug 26, 2026 · metrics 2.10.0
Go · PyPI
mensfeld/code-on-incus
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.
MITSep 20, 2026 · metrics 2.10.0
PyPI · npm · crates.io
redact-secret/redact-secret
Detect and redact secrets before they reach logs, storage, or LLM context. Deterministic Rust core for JavaScript, Python, Rust, and WebAssembly.
MITOct 10, 2026 · metrics 2.10.0
PyPI · npm
PrismorSec/prismor
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
Apache-2.0Sep 11, 2026 · metrics 2.10.0
Go · npm · PyPI
g8e-ai/g8e
A zero-trust execution platform that safely bridges AI agents and infrastructure without surrendering data sovereignty
Custom licenseSep 10, 2026 · metrics 2.10.0