Llm Security Python Packages

nemoguardrails

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

llm-guard

The Security Toolkit for LLM Interactions

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-skill-scan

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

argus-redact

Encrypt PII, not meaning. Locally.

datafog

Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.

garak

the LLM vulnerability scanner

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.

redact-secret

Detect and redact secrets before they reach logs, storage, or LLM context. Deterministic Rust core for JavaScript, Python, Rust, and WebAssembly.

giskard

🐢 Open-Source Evaluation & Testing library for LLM Agents

tulip-agents

The agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already have.

skilltotal

Claude Code plugin that scans a package before the agent runs npx, npm install, pip install, uvx or claude mcp add. Malicious indicators block the install. High-risk packages need your approval. The scan runs on your machine and never executes the code or calls an LLM. Every finding cites a file and line. Also a CLI, GitHub Action and MCP server.

squidbrake

Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.

ctrlrun

The execution safety layer for AI agents.

immunity-agent

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.)

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.

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.)

arcjet

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 Python code.

guardana-core

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

guardana-report

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

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.

guardana-rules

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

guardana-cli

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

guardana-server

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.