Llm Guardrails Python Packages

deepteam

DeepTeam is a framework to red team LLMs and AI 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.

llm-shield-proxy

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-hosted redacting gateway.

pii-leak-benchmark

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-hosted redacting gateway.

aegis-gateway-core

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

macos-computer-use-kit

AX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions kept in code. Accessibility-tree targeting, window-scoped input, clipboard-safe paste, read-back verification. Ships a pip CLI, a pi package and a DeepSeek Harness plugin.

aegis-gateway-server

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway-pack-classification

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway-sdk

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway-pack-pii

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

guardlayer

Runtime guardrails between an AI agent and its tools: scan what it reads, gate what it does, and track the session so a secret read earlier can't be exfiltrated later. Containment over detection — pure Python, zero dependencies, ~0.2 ms per tool call.

aegis-gateway-pack-residency

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway-pack-budgets

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway-cli

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

reasongate

Explainable security gate for LLM apps — blocks prompt injection with an auditable reason for every decision.

varden

Runtime security, governance and policy enforcement for AI agents

aegis-gateway-pack-llm-guard

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

agentic-security

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

mcp-ssrf-check

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-hosted redacting gateway.

aegis-gateway-pack-content

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

shadowshield

Unified open-source security shield for agentic AI systems — defense-in-depth prompt-injection protection (canary tokens, agent-trace alignment audit, tool-call guarding, PII/secret scanning).

szl-guardrail-receipt

Wrap any LLM guardrail (Llama-Guard / NeMo / guardrails-ai / your callable) and emit a signed, hash-chained DSSE decision receipt — aligned with governed-receipt-spec. UNSIGNED-honest fallback; never fabricates a signature, energy joule, or a Λ 'proven'.

cerbia-cli

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loaders, multi-layer de-obfuscation, specialized scanners, and automatic enforcement.