148,180 packages matching “agent-safety”
safety-agent
v0.1.7 · 1 month ago
An open-source SDK for AI agent safety
No known vulnerabilities
agent-safety-oss
v1.7.1 · 2 months ago
건설현장의 법정 안전문서 작성을 더 빠르고 정확하게. 산안법·기준규칙·중처법·KOSHA Guide를 기반으로 안전관리자와 현장소장의 문서 작성과 검토를 돕는 오픈소스 도구입니다.
No known vulnerabilities
@cyberdyne-systems/agent-safety
v2026.3.15 · 6 months ago
Agent safety system: stakeholder model, action validator, and safety dashboard — based on arXiv:2602.20021
No known vulnerabilities
vigil-agent-safety
v0.1.0 · 7 months ago
Zero-dependency, <2ms agent safety guardrails. Validates what AI agents DO, not what they SAY.
No known vulnerabilities
dsh-daily-bundle-dev-buddy
v0.1.0 · 1 month ago
dsh bundle: coding-agent safety & cost baseline — approval-guard + notify + cost-meter with sensible defaults
No known vulnerabilities
@openguardrails/core
v0.2.0 · 1 month ago
OpenGuardrails (OGR) reference runtime for JS/TS — a vendor-neutral enforcement protocol for AI agent safety & security: GuardEvent to Verdict, composed under a policy you own.
No known vulnerabilities
@cognitum/gate
v0.1.0 · 7 months ago
Browser and Node.js coherence gate for AI agent safety - real-time permit/defer/deny decisions in microseconds
No known vulnerabilities
open-guardrail-guards
v2.5.0 · 5 months ago
350 built-in guards for LLM safety: 26 PII regions, prompt injection, toxicity, bias, agent safety, hallucination, content safety, compliance, format validation, Korean ISMS-P/PIPA, GDPR, EU AI Act
No known vulnerabilities
agentshield-ai-sdk
v1.1.0 · 3 months ago
AgentShield SDK for AI agent safety and guardrails
No known vulnerabilities
@aigentic/cognitum-gate-kernel
v0.1.1 · 4 months ago
Browser and Node.js coherence gate for AI agent safety - real-time permit/defer/deny decisions in microseconds
No known vulnerabilities
beacon-protocol-sdk
v0.1.1 · 2 months ago
Node.js SDK for the BEACON Protocol - Agent Safety Layer
No known vulnerabilities
curiosity-cat
v0.2.0 · 2 months ago
AI agent safety framework — standing orders, danger maps, and stories that teach cats to land on their feet
No known vulnerabilities
steelclaw
v0.0.1 · 6 months ago
Steelclaw is an enterprise-grade autonomous agent. Safety first. Coming soon.
No known vulnerabilities
open-guardrail
v2.5.0 · 5 months ago
Open-source guardrail engine for LLM apps — 350 guards, 26 PII regions, 8 SDK adapters, zero API calls, <0.1ms latency, agent safety, GDPR/ISMS-P/PIPA compliance
No known vulnerabilities
guardclaw
v0.1.10 · 5 months ago
AI Agent Safety Monitor with LLM-based Command Safeguard
No known vulnerabilities
@openai/agents
v0.18.0 · 8 days ago
The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows.
No known vulnerabilities
eve
v0.62.0 · 12 hours ago
Filesystem-first framework for durable backend AI agents that run anywhere.
No known vulnerabilities
agent-base
v9.0.0 · 5 months ago
Turn a function into an `http.Agent` instance
No known vulnerabilities
vaspera-guard
v0.2.2 · 8 months ago
TypeScript SDK for VasperaGuard - AI Agent Safety & Governance
No known vulnerabilities
@metaharness/redblue
v0.1.6 · 1 month ago
AI red-teaming for the AI agents & LLM apps you own: stress-test them with adversarial models to find security failures (prompt injection, tool misuse / excessive agency, data leakage, jailbreaks, denial-of-wallet), auto-patch (blue team), retest, and get
No known vulnerabilities