Agent infrastructure
hoop
hoophq/hoop
An open-source runtime control sidecar for AI agents that masks sensitive data and blocks destructive SQL or HTTP commands on the wire, with risk analysis and human review, requiring only a port change.
Topics
Related projects
superagent6.8kAn open-source SDK for AI agent safety that blocks prompt injections, redacts PII and secrets, and scans repositories for threats. Developers embed it via TypeScript, Python, or an MCP server to guard agent deployments.
AI-Infra-Guard7.4kAn AI red-teaming platform for scanning agents, MCP servers, skills, infra CVEs, and jailbreak robustness.
opencodex18.3kopencodex is a local AI gateway that lets Codex, Claude Code, Claude Desktop, and Grok Build use many model providers, with routing, account pooling, and a management dashboard.
bifrost9.5kA high-performance open-source LLM gateway unifying 20-plus providers behind one API with failover, caching, and governance.
semantic-router6.4kAn open programmable routing and AI gateway layer that selects or blends models and compute for each agent call by policy.
metorial3.4kAn open-source identity and access control plane that sits between agents and integrations, handling authentication, scoped permissions, and auditability through unified SDKs.