Agent infrastructure
nono
nolabs-ai/nono
A zero-setup sandbox for AI agents that enforces least-privilege filesystem, network and credential policies per profile.
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.
toolhive2.3kToolHive is an open-source MCP platform that runs MCP servers in isolated containers and adds a gateway, registry, Kubernetes operator, policy enforcement and observability.
adr2.1kAn enterprise security system that observes, benchmarks, and defends AI agents in production.
astrid10.3kAn operating-system-grade runtime for AI agents that runs WebAssembly capsules with capability security, sandboxing, isolation, and auditable execution.
mirage3.8kA virtual terminal and virtual filesystem for AI agents that mounts services like S3, Slack, and Gmail under one root. It offers virtual CLIs, routed runtimes, profiles, and policy controls through Python and TypeScript SDKs.
onecli3.6kAn open-source team platform for sandboxed personal agents with credential injection, policy enforcement, memory, and shared management.