Agent infrastructure
numbat
perplexityai/numbat
Endpoint visibility and security for AI agents with local detection, optional pre-action blocking and forensic reconstruction.
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.
nono4.8kA zero-setup sandbox for AI agents that enforces least-privilege filesystem, network and credential policies per profile.
adr2.1kAn enterprise security system that observes, benchmarks, and defends AI agents in production.
emilia-protocol550Authority and security infrastructure for AI agents that checks exact authorization before consequential tool calls and produces verifiable evidence.
nasiko12kAn open runtime for managing coding agents and agent fleets, with unified cost attribution, LLM routing, orchestration, deployment, and an MCP gateway.
OmniRoute86.2kA free MIT AI gateway that exposes hundreds of providers and models through one OpenAI-compatible endpoint, with quota-aware fallback, token compression, routing strategies and MCP/A2A support.