AnythingLLM is an all-in-one AI application for private chat, document ingestion, agents, and workspace-based knowledge bases.
Launch in your Sealos workspace.
Start with the resources defined by the AnythingLLM 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.
AnythingLLM is a self-hosted AI workspace for private chat, document ingestion, agents, and retrieval-augmented generation. This template deploys AnythingLLM 1.15.0 with persistent storage and an optional Sealos-managed PGVector database.
AnythingLLM combines its web interface, API server, document collector, and agent runtime in one container. The template persists application data, uploaded documents, and collector output across restarts.
LanceDB is the default vector backend and stores vectors on the application volume. Selecting PGVector provisions a PostgreSQL 16.4 cluster through KubeBlocks, creates the anythingllm database, enables the vector extension, and waits for the database before starting AnythingLLM.
The template includes the AnythingLLM container, HTTPS ingress, and three persistent volumes. The PGVector option also includes a Sealos-managed PostgreSQL cluster and an idempotent initialization job.
Architecture Components:
/app/server/storage and collector data in /app/collector/hotdir and /app/collector/outputs.vector extension when pgvector is selected.Authentication:
The template enables AnythingLLM single-user password authentication. Set Single-user password during deployment, then enter the same password on the AnythingLLM login page. Account registration is part of AnythingLLM multi-user mode and is outside this single-user template flow.
Configuration:
vector_database selects lancedb or the managed pgvector branch.pgvector_table_name sets the embedding table name when PGVector is selected.openai_api_key optionally preconfigures an OpenAI API key; model providers can also be configured after login.License Information:
AnythingLLM is licensed under the MIT License.
Sealos provides one-click deployment, automatic HTTPS, persistent volumes, and Kubernetes-backed lifecycle management. The conditional PGVector option creates and wires the database while the platform injects database credentials directly into the workload, and pay-as-you-go resources keep personal deployments efficient.
lancedb for embedded storage, or select pgvector for a Sealos-managed PostgreSQL vector backend. Add an OpenAI API key when you want it available immediately.After login, open Settings to configure LLM and embedding providers, agent tools, appearance, and security. Use the Sealos Canvas AI dialog or resource cards for later changes to compute, storage, environment variables, and networking.
This template follows the upstream AnythingLLM 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.
Open-source AI model gateway compatible with the OpenAI API, with multi-provider routing, quota management, channel orchestration, and an admin dashboard.