Runtime for NanoClaw
NanoClaw support is coming soon as one harness inside Spinup's cloud agent runtime. The Spinup Agent stays durable above harness-local memory: isolated environment, scoped secrets, persisted state, scheduled work, and one stable endpoint for messaging skills. Today, OpenClaw and Hermes already run on this model.
Coming Soon
What NanoClaw needs from a cloud runtime
NanoClaw was built to run on your own machine with container isolation. Each piece below has to translate into the cloud before Spinup can call it supported.
Container semantics in a microVM
NanoClaw already isolates each group of agents inside a Linux container with its own filesystem and process space. The work is to map that shape onto Spinup's isolated microVM runtime.
Anthropic key projection
NanoClaw runs on the Claude Agent SDK. The Anthropic API key gets projected as a scoped secret using the same workspace model OpenClaw and Hermes already use.
Scheduling and memory that survive runs
NanoClaw supports scheduled task execution and per-group memory through CLAUDE.md files. Scheduling, memory, and the SQLite message store each need a clear persistence contract.
Messaging ingress
NanoClaw's messaging skills (WhatsApp, plus extensions for Telegram, Slack, Discord, Signal, email) need explicit ingress and lifecycle design before they can ride on a Spinup endpoint.
The Spinup Angle
A personal agent, run without a personal machine
NanoClaw was designed as a local-first agent: small enough to read in one sitting, secured by container isolation on your own machine. That design works until you want the agent to run while your laptop is asleep, reach inbound messages from anywhere, or share one agent across a small team.
You can't run NanoClaw on Spinup yet. OpenClaw and Hermes are the supported harnesses today, on the same isolated microVM, projected secrets, and persistent state model. NanoClaw's credentials, scheduling, state, and messaging land on top once each has a real shape.
NanoClaw fits the runtime model well. The work ahead is the harness-specific glue, not the architecture underneath it.
FAQ
Common questions about running NanoClaw on Spinup
How does NanoClaw's container isolation map to Spinup's environment model?+
Conceptually, the same shape: one isolated environment per agent, with explicit mounts and controlled network access. NanoClaw's Linux container becomes Spinup's microVM. NanoClaw is not a supported harness yet, so this is the mapping you'll see when it lands.
Where do the Anthropic credentials come from?+
Not yet. When NanoClaw lands, the Anthropic API key gets projected into the environment as `ANTHROPIC_API_KEY`, the same way OpenClaw and Hermes already receive their credentials. Today, OpenClaw and Hermes are the supported harnesses.
Can NanoClaw's scheduled tasks run while my laptop is off?+
Not yet. NanoClaw's scheduled tasks, message-store persistence, and CLAUDE.md memory all need a clear cloud contract first. Today, OpenClaw and Hermes are the supported harnesses.
What happens if I move from NanoClaw to another harness?+
The runtime is built to be portable across harnesses. Today the supported swap is between OpenClaw and Hermes, and NanoClaw joins the same model when it lands.
Related
The runtime should stay bigger than any one harness
Early access
NanoClaw is on the way. Try OpenClaw or Hermes on the same runtime today.
Request access if this is the runtime shape your team has been missing.