Search Packages

nemoguardrails

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

cpex

A lightweight plugin framework for building extensible AI systems

skjold

Security audit Python project dependencies against security advisory databases.

safetext

Fast profanity word, curse word, swear word, bad word filtering tool for English, Spanish, Chinese, Turkish and more.

cato-cli-py

Portable sandbox for AI agents and untrusted commands. One config, any process, anywhere.

loom-agent

Python agent framework with AgentHarness: planner → generator ⇄ evaluator loops for long-running tasks—plus sessions, tool/safety policies, and Claude, GPT, or Gemini.

acgs-lite

Constitutional governance infrastructure for AI agents — the missing safety layer between your LLM and production

sh-guard

Semantic shell command safety classifier — AST-based risk scoring for AI coding agents

rigel-hpl

High-Level Property Specification Language

jmo-security

JMo Security Audit Suite (terminal-first, multi-tool, unified outputs, multi-target scanning)

refund-guard

Safe refund policy layer for AI agents — Python + TypeScript. Same behavior, shared tests.

fmdtools

System resilience modelling, simulation, and assessment in Python

wickd-ai

Runtime safety net for AI agents - budget limits, kill switches, and approval gates

agentarmor

The full-stack safety layer for AI agents. Budget limits, prompt injection shields, PII filtering, output firewalls, and hooks — in 2 lines of code.

hpl-specs

High-level Property Specification Language

ramstk

Reliability, Availability, Maintainability, Safety (RAMS) analysis program.

simplesecurity

Combine multiple popular python security tools and generate reports or output into different formats

claude-safety-guard

A zero-dependency Claude Code PreToolUse guard that blocks destructive shell commands before they run.

proofagent

pytest for AI agents — test safety, accuracy, tool use, and cost. No YAML, no telemetry, just Python.

agent-integrity-proto

Agent Integrity Protocol — real-time thinking block analysis for AI agent alignment

model-action-protocol

MAP (Model Action Protocol) — Cryptographic provenance, self-healing critic, and state rollback for autonomous AI agents. 2.5k lines of TypeScript, 60+ tests, MIT.

cognilateral-trust

AI that tells you when it's guessing. Confidence tiers + accountability for AI agents. pip install cognilateral-trust

grid-intelligence

GRID - Geometric Resonance Intelligence Driver: A comprehensive framework for exploring complex systems through geometric resonance patterns, cognitive decision support, local-first AI, and event-driven agentic systems

gymkhana

Custom gym environment for training Deep Reinforcement Learning policies to race and drift on 1/10 scale or full-size Ackermann vehicles. SB3 and wandb integration. Based on the f1tenth_gym simulator built by UPenn