Namespace-bounded containment for AI agents, built on a 64-bit Inferno® OS. 9P everywhere, formally verified isolation, 15–30 MB of RAM, MIT licensed.
Run agents in isolated cells that borrow verified tools instead of rebuilding Linux environments.
Run AI coding agents in secure, isolated microVMs. Sub-125ms boot times, real hardware isolation.
Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrough, MCP-native CLI
Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.
Container-free, deny-by-default sandbox for AI coding agents. Kernel-enforced filesystem, network, and syscall isolation for Linux and macOS
Selectively permeable boundary for AI agents
The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.
Manager for podman containers for AI coding agents