A self-hosted AI agent with a browser workspace, persistent conversations, tools, memory, and scheduled tasks.
Launch in your Sealos workspace.
Start with the resources defined by the nanobot template. Review CPU, memory, persistent storage, and network allocations for every service in Canvas. Capacity needs depend on your data and workload; monitor usage as they grow.
Template configuration and setupUse the application URL or connection details shown in Canvas. Follow the deployment guide for first-time account setup or client configuration, and keep generated credentials available for that step.
Sealos monthly plans include compute, memory, storage, and traffic. Size your plan for all deployed services. Software licenses and external AI or API services may have separate terms and charges. Confirm the applicable plan and optional charges in Cost Center.
Compare Sealos resource plansFor current cloud charges, refer to Sealos plan pricing. Upstream documentation may reference earlier billing models.
nanobot is a self-hosted AI agent with a browser workspace, tools, memory, and scheduled tasks. This template deploys the nanobot gateway and its bundled WebUI with persistent storage on Sealos Cloud.
The gateway serves the WebUI and authenticated WebSocket connections together on port 8765. A single instance stores its configuration, conversations, memory, generated files, and automation state on a 1Gi persistent volume.
The template initializes the configuration once, prepares the tokenizer cache before startup, and preserves settings edited in the WebUI across restarts. Browser access uses the password you set in the deployment form. File tools start with workspace restrictions enabled.
The template includes the Python runtime, bundled WebUI, built-in tools, and persistent storage. Provide an API key, an OpenAI-compatible API base URL, and an exact model ID from the same provider.
| Component | Configuration |
|---|---|
| Release | nanobot v0.3.0 |
| Runtime | One gateway with the bundled WebUI, running as UID 1000 |
| Storage | 1Gi at /home/nanobot/.nanobot |
| Configuration | /home/nanobot/.nanobot/config.json, initialized on first start |
| Model provider | OpenAI-compatible endpoint selected by the deployment inputs |
| Public entry | HTTPS WebUI with WebSocket support on port 8765 |
| Health endpoint | Container-local port 18790 |
| Validated low-load limits | Gateway: 200m CPU / 256Mi memory; initialization: 100m CPU / 128Mi memory |
The image ghcr.io/yangchuansheng/sealos-template-init:nanobot-v0.3.0 is built from the unmodified upstream v0.3.0 Dockerfile and source. The selected upstream deployment stores data in local files; this template provisions the corresponding persistent volume. Keep one replica for this shared local-state runtime.
Sealos provides Kubernetes scheduling, persistent storage, HTTPS routing, and pay-as-you-go resources for the gateway. After deployment, use the Canvas AI dialog or resource cards to adjust resources and inspect logs.
https://api.openai.com/v1.web_token value in Password, and click Connect. This shared-password flow opens the WebUI directly.Use Settings → Models to manage model settings and Settings → Channels for chat integrations. Configuration changes are stored on the persistent volume; follow any restart notice shown by the WebUI. Deployment provider values remain available through OPENAI_API_KEY, OPENAI_API_BASE, and NANOBOT_MODEL.
The browser remembers its access password locally. Enter the same deployment password when connecting from a new browser or after clearing browser storage. Its current value is available as NANOBOT_WEB_TOKEN in the gateway resource card. The gateway uses a shared access password, with each trusted user able to operate the same agent workspace.
Remote installation of optional Python packages starts disabled. The default image includes WhatsApp support; other channels may require an image rebuild with the upstream NANOBOT_CHANNELS build argument before enabling them.
NANOBOT_WEB_TOKEN value from the gateway resource card and enter it without extra whitespace.This Sealos template follows the templates repository license. nanobot is licensed under the MIT License.
A shorter path from an app you want to an app you can run. Sealos brings deployment and ongoing operations into one place.
Start with a ready-made template. Review its configuration and launch from the Sealos console.
Run on managed infrastructure with built-in workload scheduling and recovery.
Give your application a public HTTPS endpoint with certificates managed for you.
Keep application data on persistent volumes across container restarts.
Adjust CPU, memory, and replicas from the console as your workload changes.
Sealos provisions the resources defined by your template and brings them together in your workspace.
Container workloads with configurable CPU, memory, and replicas.
An address for your app, with managed TLS certificates.
A database provisioned alongside your app when the template calls for one.
Storage for the files and data your application needs to keep.
Application settings and secrets configured in one place.
Inspect container logs and resource usage from the console.
Resources and their configuration vary by template. Review the deployment form for this app’s exact setup.
Explore more production-ready templates.
Build production-ready ai templates with Sealos.
Open Design is a local-first, open-source AI design workspace for generating prototypes, decks, images, videos, and design-system-driven artifacts.
Build production-ready ai templates with Sealos.
Host OpenClaw's AI agent gateway on Sealos with a browser control panel, token authentication, and persistent storage for configuration and workspaces.
Build production-ready ai templates with Sealos.
Host n8n workflow automation on Sealos with persistent storage and HTTPS webhooks. Choose PostgreSQL and Redis-backed queue mode as your workflows grow.