LobeChat hosting
A fast, polished chat UI with a large plugin and assistant marketplace.
LobeChat hosting at AIHostBox means a dedicated, single-tenant LobeChat instance on our infrastructure: we install it, pin it to a reviewed release, put it behind TLS on your domain, back it up nightly and keep it patched. Plans start at $11.99 per month and the admin account, the data and any API keys are yours.
LobeChat is the chat and agent workspace built by LobeHub LLC, now shipped under the LobeHub name. Where most self-hosted chat front-ends look like admin tools, this one is designed like a consumer app: an agent marketplace, a plugin and MCP skill library, file uploads with vision, voice input, scheduled agent runs and shared workspaces. It talks to OpenAI, Anthropic, Google, Azure, Bedrock, DeepSeek, OpenRouter, Ollama and dozens more providers from one interface, so colleagues can switch models without learning a new tool.
Version 2 changed what running it means. The old browser-only mode, where conversations lived in each user’s local database, was removed; every deployment is now a server with PostgreSQL for data, an S3-compatible bucket for uploads and Redis for sessions and queues. That is what makes shared agents, multi-device history and team logins possible, and it is also why LobeChat belongs on a server that is always on, backed up and reachable at your own domain rather than on a laptop.
LobeChat hosting plans
Every plan is a dedicated single-tenant instance with NVMe storage, nightly off-box backups, TLS and managed patching. Quarterly, semi-annual and annual terms are discounted at checkout. Model tokens are not included — you bring your own key.
How we run LobeChat
We run the official LobeHub v2 server stack: the lobehub/lobehub app container on port 3210, PostgreSQL (the ParadeDB image with pg_search), Redis, RustFS as the S3-compatible file store and the LobeHub agent gateway; the optional Elasticsearch search profile stays off.
What we configure for you
- KEY_VAULTS_SECRET, AUTH_SECRET and JWKS_KEY generated per instance, never reused
- APP_URL set to your domain so Better Auth callbacks and SSO work over TLS
- S3_ENDPOINT, S3_BUCKET and access keys wired to the bundled RustFS bucket for uploads
- Provider keys such as OPENAI_API_KEY or ANTHROPIC_API_KEY, or OLLAMA_PROXY_URL for a local model
- AUTH_SSO_PROVIDERS and AUTH_ALLOWED_EMAILS if you want organisation-only logins
- SMTP_HOST and related settings for email verification and password resets
Which plan fits
Plus (4 GB) runs the full stack comfortably for an individual or a small team using hosted model APIs. Pro (8 GB) suits a team with heavier file uploads and knowledge work, or several people running scheduled agents at once. Neither plan runs a local model inside LobeChat itself; pair it with an Ollama instance if you want one.
The honest limits
The LobeHub Community Licence is Apache 2.0 with extra terms: running it commercially unmodified is allowed, but distributing a modified derivative needs a commercial licence from LobeHub. Some features advertised on lobehub.com, such as cloud sandboxes, depend on LobeHub’s own hosted services.
What people run LobeChat for
Consumer-grade internal tool
Give non-technical colleagues an interface they do not need training for.
Assistant library
Install ready-made assistants from the marketplace instead of writing prompts.
One front-end for many providers
Put OpenAI, Anthropic, Gemini and a local Ollama model behind the same login and let people pick per conversation.
Scheduled agent work
Set an agent to run at a fixed time, such as a morning digest, and read the result when you log in.
Licence and version policy
| Item | Position |
|---|---|
| Upstream licence | LobeHub Community License |
| Sold as managed hosting | Yes |
| Tenancy | Single tenant — one customer per instance |
| Patching | Critical advisories within 24 hours, high severity within 72 |
Our full position on licences, including the applications we decline to sell, is on the licensing page.
Works well with LobeChat
Ollama
Your private LLM server — pull a model, get an API, keep every token on your own box.
from $16.99/moDetails →
LiteLLM
One OpenAI-compatible endpoint in front of every model provider you use.
from $5.99/moDetails →
SearXNG
A private metasearch engine — and the search backend your agents need.
from $5.99/moDetails →More AI assistants & chat we host
OpenClaw
Your always-on personal AI assistant, running 24/7 on a server you control.
from $9.99/moDetails →
Open WebUI
A ChatGPT-style workspace for your team, pointed at any model you like.
from $5.99/moDetails →
LibreChat
Multi-model chat with agents, plugins and conversation forking.
from $11.99/moDetails →
SillyTavern
The character-driven chat front-end, online wherever you are.
from $5.99/moDetails →LobeChat hosting: your questions
Is LobeChat the same thing as LobeHub?
Which model providers can I connect?
Can we sign in with Google, Microsoft or our own identity provider?
I used LobeChat v1 in local database mode. Can I bring my chats across?
What does the backup cover?
Run LobeChat without running a server
A dedicated LobeChat instance, deployed and maintained by us. Month to month, cancel whenever.