Show HN: OpenClawMachines – Extending OpenClaw to the Enterprise OpenClawMachines, an open-source platform for running isolated OpenClaw agents in Firecracker microVMs on self-owned hardware, was released. The platform provides a control plane, host agent, LLM proxy, and browser runtime for secure AI sandboxing with hardware isolation and edge auth. It aims to offer cost-effective, sovereign AI infrastructure for enterprises. Run as many isolated OpenClaw agents as you need, on hardware you own. OpenClaw Machines is an open-source platform for running OpenClaw in secure AI sandboxes on your own infrastructure . A control plane orchestrates your hosts, and each agent runs in its own Firecracker https://github.com/firecracker-microvm/firecracker microVM on them — hardware-isolated, safe for untrusted and agent-generated code. A Cloudflare data plane is the front door: every machine gets its own subdomain behind edge auth, reached through a tunnel that terminates inside the VM — no host port is exposed for user-to-VM traffic. The current control plane still needs private or firewall-restricted access to each agent's authenticated control API on 9090 . See it running at openclawmachines.com https://openclawmachines.com . The Apache-2.0 public core ships every piece of that stack: - a — Go API, Postgres-backed accounts, machines, and hosts; minimal control plane placement /mathaix/OpenClawMachines/blob/main/docs/architecture.md scheduling--capacity-management , machine lifecycle /mathaix/OpenClawMachines/blob/main/docs/architecture.md machine-lifecycle , host enrollment /mathaix/OpenClawMachines/blob/main/docs/host-enrollment.md , backups /mathaix/OpenClawMachines/blob/main/docs/architecture.md backup--restore , and durable workflows /mathaix/OpenClawMachines/blob/main/docs/architecture.md durable-workflows-dbos ; - the host agent ocm-agent — boots, supervises, and reaps Firecracker microVMs on your enrolled Linux boxes, managing bridge/TAP networking and rootfs staging; - a per-host LiteLLM — one place for model keys and BYO-key support, with per-machine usage tracking across providers or your own locally served models ; LLM proxy - the — the in-VM pieces: auth proxy, web-chat gateway, live terminal, and the artifact-driven runtime staging/upgrade flow; OpenClaw runtime - the — paired Chromium browser VMs with CDP routing and a watchable live view; browser runtime — GitHub, Google Workspace, OpenAPI, GraphQL, and remote-MCP tools connected once per workspace and exposed to machines through the OCM MCP facade; workspace integrations / native MCP - and the that assemble it all — every component's build command, the GCS artifact bucket layout, host provisioning scripts, and the build pipelines release lanes /mathaix/OpenClawMachines/blob/main/docs/ci-release.md . The ocm CLI lives in the separate mathaix/ocm-cli https://github.com/mathaix/ocm-cli Apache-2.0 repository. Click the screenshot to watch the 43-second demo on YouTube. This is a linked image, not an embedded player. The demo covers host onboarding, agent spin-up, the running Firecracker VM terminal, workspace MCP integrations, and an agent tool call end to end. Security. Real isolation, not containers: one Firecracker microVM per agent, with its own guest kernel behind a KVM hardware boundary — and auth enforced at the edge and again inside every VM. Cost. One flat server cost: rent a single bare-metal box and run as many hardware-isolated agents as it fits — see how the options compare how-the-options-compare . The same architecture cuts token spend too: route agents to open-source models running on your own GPU hardware instead of paying per-token APIs. Sovereignty. Your hardware, your data, your keys. Run the control plane and workers on machines you own, and route model traffic through the per-host LLM proxy to any provider — or to models served on your own GPUs. Open source. Apache-2.0 public core and companion, permissively licensed for adoption, embedding, and contribution. ocm CLI Enterprise. Multi-user accounts and teams, admin-gated host management, encrypted per-machine secrets, and capacity/placement policies across your fleet. Ecosystem. Browser VMs for web automation, live terminal and web chat, per-VM routing, workspace-scoped native MCP integrations, backups/snapshots, agent memory, and observability with OpenTelemetry/Opik tracing and per-machine usage tracking. If you run OpenClaw https://github.com/openclaw/openclaw today, you have a few options: Local hardware — run it on your own laptop or desktop. A VPS e.g. Hostinger, DigitalOcean — rent a virtual server and run it there. A managed service e.g. KiloClaw — spin up a hosted OpenClaw instance and pay per instance. OpenClaw Machines is the fourth option : rent one bare-metal server OVHcloud, Hetzner, … , point OpenClaw Machines at it, and spin up as many hardware-isolated OpenClaw instances as the box will hold. One agent or fifty — the cost stays one flat server . In short: the managed route is easiest but priced per agent; local and VPS are cheap to start but don't isolate or scale well. OpenClaw Machines trades a little more setup for the best economics and isolation once you're running more than a couple of agents — one server, many hardware-isolated agents, all yours. OpenClaw Machines turns your own Linux servers into a pool of secure, on-demand sandboxes. Each sandbox is a real Firecracker microVM its own kernel, hardware-isolated via KVM that runs one AI agent. The platform is the control plane that creates those VMs, keeps track of them, routes traffic to them, and tears them down — so you can run many untrusted agents safely on infrastructure you own. Think: a mini-cloud for AI agents, that you self-host. Control plane Go backend — the brain. Accounts, machines, hosts, and config; the API the UI/CLI call; placement and lifecycle orchestration. Hosts + worker agents — your Linux boxes. Enroll a host with an install script; its worker agent boots and stops Firecracker microVMs when told to. Machines — one isolated microVM per agent. Inside: the OpenClaw agent, a web chat gateway, and a live terminal. Browser VMs — separate microVMs running headful Chromium with a live view, driven by the agent over CDP for browser automation. Routing / data plane — every running VM gets its own subdomain and a Cloudflare Tunnel that terminates inside the VM , with auth enforced at the edge and again in-VM. Workspace integrations native MCP — connect external tools once per workspace GitHub, Google Workspace, or any OpenAPI / GraphQL / remote-MCP endpoint ; the control plane exposes them to each machine's agent through a single built-in MCP server, so the agent discovers and calls them with ocm.search tools / ocm.call tool instead of per-integration wiring. php flowchart TB U "you — browser / ocm CLI" -- EDGE "Cloudflare edge