16 packages
ai-agent-discovery
Enterprise tool for discovering AI Agents running within an organization
n8n-nodes-openguardrails
n8n node for OpenGuardrails AI safety and content moderation
og-openclawguard
Agent-based prompt injection detection for OpenClaw powered by OpenGuardrails SOTA security
@openafw/openafw
The local firewall for AI agents: route and repair them, and keep your secrets off the model, the API relay, and the supply chain. Local credential masking, per-route model routing, and security detectors on the wire. Free and fully open source.
openguardrails
Runtime security for AI agents — behavioral detection, PII sanitization, and management dashboard
@openguardrails/agentfw
The local firewall for AI agents: route and repair them, and keep your secrets off the model, the API relay, and the supply chain. Local credential masking, per-route model routing, and security detectors on the wire. Free and fully open source.
openguardrails-for-openclaw
Agent-based prompt injection detection for OpenClaw powered by OpenGuardrails SOTA security
@openguardrails/gateway
AI Security Gateway — secure proxy for LLM APIs with PII sanitization, credential detection, and content security
@openguardrails/moltguard
AI agent security plugin for OpenClaw: prompt injection detection, PII sanitization, and monitoring dashboard
@openguardrails/openclaw-plugin
AI agent security plugin for OpenClaw: prompt injection detection, PII sanitization, and monitoring dashboard
@openguardrails/openclaw-security
AI agent security plugin for OpenClaw: prompt injection detection, PII sanitization, and monitoring dashboard
@openguardrails/thomas
Thomas is the plug-and-play model hub that connects your agents to your models, with security guardrails, quotas, fallback, and cost controls.
openthomas
Open-source Bayesian trading worker for prediction markets. Named after Thomas Bayes. v0: 2026 World Cup moneyline forecasts on Polymarket, auditable belief ledger, WorkPnP worker client, dry-run edge/Kelly intents.
@openthomas/thomas
Give vision-blind coding models eyes (DeepSeek + Qwen3.6, any agent). See cost per task, not per model. The dynamic harness for your agent fleet — Free for See; Control + Govern paid.
@trustunknown/thomas
Thomas is the plug-and-play model hub that connects your agents to your models, with security guardrails, quotas, fallback, and cost controls.
xiangxinai
An LLM-based context-aware AI guardrail capable of understanding conversation context for security, safety and data leakage detection.