PyRank
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About

Ai Safety Python Packages

Python packages with the GitHub topic ai-safety. Sorted by relevance, with stars and monthly downloads.
vstorm-co
pydantic-ai-shields

Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction, tool permissions, and async guardrails. Built on pydantic-ai's native capabilities API.

110K 63 10
vstorm-co
pydantic-ai-middleware

Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction, tool permissions, and async guardrails. Built on pydantic-ai's native capabilities API.

82K 63 10
microsoft
agent-governance-toolkit

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

65K 2K 338
microsoft
agent-os-kernel

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

61K 2K 338
microsoft
agentmesh-platform

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

51K 2K 338
microsoft
agent-sre

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

49K 2K 338
microsoft
agent-hypervisor

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

49K 2K 338
microsoft
agentmesh-runtime

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

40K 2K 338
yohanpoul
etzchaim

A diagnosable brain for your LLM. Cognitive architecture in the SOAR/ACT-R/CLARION/LIDA lineage, for the LLM era. Apache 2.0.

28K 1 0
microsoft
agentmesh-primitives

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

21K 2K 338
yesonsys03-web
vibelign

AI coding safety CLI for vibe coding workflows. Checkpoints, undo, anchors, MCP, and secret protection for Claude Code, Cursor, Codex, and OpenCode.

17K 19 1
fathom-lab
styxx

Cognitive observability for LLM agents. Cognometric instruments + self-healing reflex (F10) + MCP server. Pure-Python, MIT, no LLM required. 9-for-9 on K=1 phase transition. Every Mind Leaves Vitals (DOI 10.5281/zenodo.19777921).

16K 5 1
vaaraio
vaara

Adaptive AI Agent Execution Layer — risk scoring, audit trails, regulatory compliance (EU AI Act Article 14)

13K 1 0
gautamvarmadatla
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.

11K 6 1
sunglasses-dev
sunglasses

Sunglasses for AI agents. Protection layer + neighborhood watch.

10K 1 1
sattyamjjain
agent-audit-kit

Static scanner for MCP-connected AI agent pipelines — 200 rules across 11 categories, 12 compliance frameworks, OWASP Agentic 10/10 + MCP 10/10, GitHub Action, SARIF, 48h CVE-to-rule SLA.

8K 5 0
yzhao062
anywhere-agents

One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

8K 173 19
XSafeAI
xsafeclaw

XSafeClaw - Keeping Your Claw Safe. Real-time monitoring and security for OpenClaw, Hermes, and nanobot AI agents.

7K 151 6
jeranaias
signet-sign

Capability-based safety gates for LLM agents. The model proposes; signet authorizes.

7K 0 0
johnnichev
selectools

Production-ready Python framework for AI agents with built-in guardrails, audit logging, cost tracking, and hybrid RAG. Supports OpenAI, Anthropic, Gemini, Ollama. By NichevLabs.

6K 9 2
mosquito
axio

Axio — Asynchronous eXtensible Intelligent Orchestration. A minimal, streaming-first, protocol-driven foundation for LLM-powered agents.

6K 0 0
MaxMLang
pytector

Easy to use LLM Prompt Injection Detection and Prompt Input Sanitization / Detector Python Package with support for local models, API-based safeguards, and LangChain guardrails.

6K 41 23
rozmiarD
govengine

Carrier-agnostic governed execution services that consume SCLite contract lifecycle artifacts for policy-gated security automation.

6K 0 0
ariffazil
arifos

ArifOS — Constitutional MCP kernel for governed AI execution. AAA architecture: Architect · Auditor · Agent. Built for the open-source agentic era.

6K 43 9
    • Data from PyPI, GitHub, ClickHouse, and BigQuery