PyPI · npm
NVIDIA-NeMo/Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Licencia propia17 sept 2026 · métricas 2.10.0
Todas las etiquetas
Etiqueta del catálogo
#safety
Todos los repositorios del registro público que llevan esta etiqueta, procedente de sus topics de GitHub o de las palabras clave que publican sus registros de paquetes. La salud se mide con la misma metodología versionada que el resto del registro.
37 registros
npm
openai/openai-guardrails-js
OpenAI Guardrails - TypeScript / JavaScript
MIT13 sept 2026 · métricas 2.10.0
crates.io · Go
contextforge-org/cpex
A policy enforcement runtime for AI agents
Apache-2.010 sept 2026 · métricas 2.10.0
PyPI
pyupio/safety
Safety checks Python dependencies for known security vulnerabilities and suggests the proper remediations for vulnerabilities detected.
Licencia propia27 ago 2026 · métricas 2.10.0
npm
cobusgreyling/loop-engineering
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
MIT28 ago 2026 · métricas 2.10.0
npm · PyPI
mnemom/aip
Agent Integrity Protocol — real-time thinking block analysis for AI agent alignment
Apache-2.03 oct 2026 · métricas 2.10.0
Packagist
nette/latte
☕ Latte: the safest & truly intuitive templates for PHP. Engine for those who want the most secure PHP sites.
Licencia propia21 oct 2026 · métricas 2.10.0
Packagist
phpstan/phpstan-strict-rules
Extra strict and opinionated rules for PHPStan
MIT27 ago 2026 · métricas 2.10.0
npm
arthurfiorette/prisma-json-types-generator
⚒️ Changes JsonValues to your custom typescript type.
MIT18 oct 2026 · métricas 2.10.0
PyPI
SepineTam/mcp-for-stata
A MCP server for integrating Stata into your agent loop with a safety-first design.
AGPL-3.014 sept 2026 · métricas 2.10.0
PyPI
jimmy058910/jmo-security-repo
JMo Security Suite - Terminal-first security audit toolkit with many tools, multi-target scanning, & compliance
Licencia propia15 sept 2026 · métricas 2.10.0
npm
IgorGanapolsky/ThumbGate
ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.
MIT11 sept 2026 · métricas 2.10.0
PyPI
shelkesays/safelint
SafeLint enforces safety-critical coding practices inspired by Gerard J. Holzmann’s “Power of Ten” rules, adapted for modern AI-assisted software development.
MIT9 oct 2026 · métricas 2.10.0
crates.io
Dicklesworthstone/destructive_command_guard
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.
Licencia propia28 ago 2026 · métricas 2.10.0
PyPI
Raccoon-Office/Box-Agent
AI agent framework with Jupyter sandbox, data analysis, MCP tools, ACP protocol, multi-provider LLM, and standalone runtime packaging
MIT20 oct 2026 · métricas 2.10.0
PyPI
Sahil170595/quantfit
Quantize an LLM and check it still refuses what it should — a GPU-aware quantization CLI that measures the safety drift of the quantization it just performed.
Apache-2.012 oct 2026 · métricas 2.10.0
npm
cendorhq/cendor-libs-js
Production plumbing for LLM apps in TypeScript: context, cost, testing & governance primitives. Python-interoperable.
Apache-2.021 oct 2026 · métricas 2.10.0
npm · crates.io
pulseengine/rivet
Rivet — SDLC traceability for safety-critical systems. Schema-driven artifact management, validation, and lifecycle linking. Part of the PulseEngine toolchain.
Sin licencia11 sept 2026 · métricas 2.10.0
PyPI · npm
QWED-AI/qwed-open-responses
Verification guards for OpenAI Responses API - Verify AI agent outputs before execution
Apache-2.018 sept 2026 · métricas 2.10.0
Packagist · npm
nette/forms
📝 Generating, validating and processing secure forms in PHP. Handy API, fully customizable, server & client side validation and mature design.
Licencia propia20 oct 2026 · métricas 2.10.0
PyPI
tuliplabs-ai/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.
Apache-2.08 oct 2026 · métricas 2.10.0
Go
Dicklesworthstone/slb
Two-person rule CLI for AI coding agents: peer review and approval required before running potentially destructive commands
Licencia propia19 oct 2026 · métricas 2.10.0
PyPI
cendorhq/cendor-libs
Production plumbing for LLM apps: context, cost, testing & governance — composable, framework-agnostic Python libraries.
Apache-2.021 oct 2026 · métricas 2.10.0
npm
mickelsamuel/migrationpilot
PostgreSQL migration linter. Blocks unsafe migrations before merge: 112 rules, the real Postgres parser, lock analysis, auto-fix. CLI, GitHub Action, MCP.
MIT18 sept 2026 · métricas 2.10.0
PyPI
DeepAgentLabs/agentic-sidecar
Companion intelligence for autonomous agents with real-time supervision, escalation, and human approval loops.
MIT11 oct 2026 · métricas 2.10.0
—
MilesCranmer/DispatchDoctor.jl
The dispatch doctor prescribes type stability
Apache-2.014 sept 2026 · métricas 2.10.0
Go
gontract/gontract
A require-ensure-library for contract-programming with pre- and postconditions in golang
LGPL-3.010 sept 2026 · métricas 2.10.0
npm
subodhkc/llmverify-npm
AI model health monitor for LLM apps – runtime checks for drift, hallucination risk, latency, and JSON/format quality on any OpenAI, Anthropic, or local client.
Licencia propia20 sept 2026 · métricas 2.10.0
crates.io
awxkee/pic-scale-safe
Fast and safe image scaling in Rust
BSD-3-Clause18 sept 2026 · métricas 2.10.0
Go
marcelocantos/doit
Agentic gatekeeper for Claude Code — three-level policy engine, Starlark rules, per-project config
Apache-2.025 sept 2026 · métricas 2.10.0