Skip to main content

Documentation Index

Fetch the complete documentation index at: https://noradocs.solomontsao.com/llms.txt

Use this file to discover all available pages before exploring further.

Nora gives you a single place to deploy and operate AI agent runtimes. From the Deploy page you configure a name, resource allocation, and sandbox type, then Nora queues the deployment, provisions the container, and brings the agent online. Once an agent is running, you can chat with it, inspect its logs, and open an interactive terminal — all from the same dashboard.

Before you start

Make sure you have at least one LLM provider key saved in Settings before deploying. Agents need a provider key to run chat workflows. See Add and sync LLM provider keys to set one up.

Deploy an agent

1

Open the Deploy page

Navigate to Deploy in the sidebar. This is the starting point for every new agent.
2

Enter a name

Type a name for your agent. Names are limited to 100 characters. If you leave the field blank, Nora generates a default name such as OpenClaw-Agent-472.
3

Choose a sandbox type

Select the sandbox that will run your agent. See the sandbox comparison table below for details on each option.
4

Set resource limits

Specify the vCPU count, RAM (MB), and disk size (GB) for the agent container. In self-hosted mode these values are clamped to the operator-configured limits. In PaaS mode they are fixed to your subscription plan.
5

Confirm and deploy

Click Confirm & Deploy Agent. Nora creates the agent record with a queued status and adds a deployment job to the queue.

What happens during deployment

After you click Confirm & Deploy Agent, the deployment moves through two stages:
  1. Queued — The agent record is created and a deployment job is queued. The status is set to queued immediately so you can track progress.
  2. Running — Nora provisions the container and starts the agent runtime. The status transitions to running once the container is live.
If the container cannot start, the status transitions to error or warning. From either of those states you can redeploy the agent (see below).

Lifecycle actions

Once an agent exists you can manage it from its detail page. The following actions are available:
ActionWhen availableWhat it does
StartAgent has a container but is stoppedStarts the existing container and sets status to running
StopAgent is runningStops the container and sets status to stopped
RestartAgent has a containerRestarts the container in place and keeps status running
RedeployAgent is in warning, error, or stopped stateClears the old container assignment and queues a fresh deployment with the same specs
DeleteAny stateDestroys the container (if any) and permanently removes the agent record
Deleting an agent is irreversible. The container is destroyed and all associated data is removed.

Access chat, logs, and terminal

From an agent’s detail page you can:
  • Chat — Send messages to the agent runtime using the OpenClaw chat interface with streaming responses.
  • Logs — View live and historical log output from the agent container.
  • Terminal — Open an interactive terminal session connected to the running agent.
The chat and terminal tabs are only available while the agent status is running. Logs are accessible regardless of status.

Sandbox types

Nora supports two sandbox types. Choose the one that fits your security and model requirements.
FeatureStandard sandboxNemoClaw sandbox
RuntimeOpenClaw + DockerNemoClaw + OpenClaw
Underlying runtimeDocker containerDocker-hosted NemoClaw container
Policy controlsNoneOpenShell allow/deny policies
Supported modelsAny configured LLM providerNVIDIA Nemotron models only
Approval workflowNoYes — operator reviews flagged actions
Operator requirementNoneNEMOCLAW_ENABLED=true must be set
Use caseGeneral-purpose agentsSecurity-sensitive or compliance workflows
If you select the NemoClaw sandbox and NEMOCLAW_ENABLED is not set to true in your environment, deployment will return an error. Ask your operator to enable it first.
For a full guide to NemoClaw agents, see Run secure agents with NemoClaw sandboxes.