An open-source AI agent development platform with integrated workflow, knowledge, memory, plugin, and chat capabilities.
Launch in your Sealos workspace.
Start with the resources defined by the Coze Studio 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.
Coze Studio is an open-source platform for building AI agents with workflows, knowledge bases, memory, plugins, and chat experiences. This template deploys the Coze Studio 0.5.1 runtime bundle on Sealos Cloud with managed databases, search, vector storage, object storage, and an HTTPS entry.
The template keeps the application services and their stateful dependencies in one Sealos deployment. Coze Studio stores relational state in KubeBlocks MySQL, uses KubeBlocks Redis for cache and session state, NSQ for messaging, Elasticsearch for search indexes, Milvus for vectors, and a private Sealos Object Storage bucket for uploaded assets.
The generated hostname is wired into the web Ingress and the server's public URL. Persistent volumes keep etcd, Elasticsearch, Milvus, and migration work data across pod restarts.
The deployment contains these runtime components:
80, published through the HTTPS Ingress and Sealos App entry.8888 and 8889.nsqlookupd and nsqd provide internal message delivery.9.1.2 stores Coze search indexes.v2.5.10 provides the vector store and uses the private object-storage bucket.ac-mysql-8.0.30-1 and Redis redis-7.2.7 provide application state and cache.Sealos is an AI-assisted Cloud Operating System built on Kubernetes. It provisions the multi-service runtime, managed databases, storage, TLS, and service discovery from one template, so you can focus on agent design.
Enter both values in the deployment dialog:
| Name | Description | Required | Default |
|---|---|---|---|
api_key | Ark API key used by the default model configuration. | Yes | None |
model_id | Ark model or endpoint ID used by Coze Studio. | Yes | None |
The template generates plugin encryption secrets and database credentials. Keep your Ark key private and rotate it through the Sealos resource configuration when needed.
api_key and model_id in the parameter dialog./sign, enter an email and password, and click Register. Coze Studio redirects the new account to its workspace. Existing users use the same form and click Log in.Coze Studio uses a private object-storage bucket for uploaded files and default plugin icons. The template also provisions 1 GiB persistent volumes for etcd, Elasticsearch, Milvus, and the server migration workspace. Sealos is built on Kubernetes and uses pay-as-you-go resources; increase the relevant resource cards and storage volumes in Canvas when data size or traffic grows. Use the Canvas AI dialog for environment changes and the resource cards for direct tuning.
The server migration and index jobs are idempotent. Restarting a workload keeps database state and persistent files, while a deployment deletion follows the template's managed resource retention policy.
Wait until the server and web workloads report Ready. The server waits for MySQL, Redis, NSQ, Elasticsearch, and Milvus before it starts accepting traffic.
Inspect the Elasticsearch health and index-init container logs in Canvas. Confirm that the Elasticsearch resource has Ready status and that the project_draft and coze_resource indexes exist.
Check that api_key and model_id match an active Ark credential and endpoint. Update the values in the Sealos configuration and restart the server workload.
This Sealos template is provided under the templates repository license. Coze Studio remains subject to the license and terms published by its upstream project.
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.