Agent infrastructure
adr
uber/adr
An enterprise security system that observes, benchmarks, and defends AI agents in production.
Topics
Related projects
hol-guard1.1kA local-first security layer for AI agents that reviews shell commands, file access, packages, plugins, and MCP calls before they run.
skillspector24.9kA security scanner for AI agent skills that detects prompt injection, exfiltration, and supply-chain risks before install.
nono4.8kA zero-setup sandbox for AI agents that enforces least-privilege filesystem, network and credential policies per profile.
emilia-protocol550Authority and security infrastructure for AI agents that checks exact authorization before consequential tool calls and produces verifiable evidence.
holaOS11.4kA local-first agentic workspace that hosts Claude Code, Codex, and its own agent with shared memory, skills, and apps.
mcp-agent8.6kA Python framework for building MCP-native agents with composable router, orchestrator, and swarm patterns plus durable Temporal execution for production applications.