LobeHub (LobeChat)
Polished multi-model chat and agent workspace with plugins and knowledge bases.
Quick answer
LobeHub (LobeChat) is a polished multi-model chat and agent workspace with plugins and knowledge bases, listed under Private ChatGPT-style chat. A typical small-business use: team chat portal with a marketplace of pre-built assistants. Official hardware: minimum 2 vCPU · 4 GB RAM · 20 GB disk (recommended 4 vCPU · 8 GB RAM · 50 GB disk). That fits a Hetzner Cloud CPX22 server at about €19.99/month (server only, excl. VAT; €35.99/month for the recommended spec). License: LobeHub Community License (Apache-2.0 with conditions), which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 22, 2026.
What is LobeHub (LobeChat)?
LobeHub, formerly LobeChat, is a modern chat interface supporting many model providers, function calling, plugins, agents and file uploads. The Docker Compose deployment bundles a database, object storage and Redis for multi-user use.
Where it fits in a 10–200 person business
- Team chat portal with a marketplace of pre-built assistants
- Agent workspace for marketing or content teams
- Multi-provider chat with server-side history
These use cases are our editorial suggestions, not claims made by the project.
Can a business use LobeHub (LobeChat)? (license)
| License | LobeHub Community License (Apache-2.0 with conditions) |
|---|---|
| Type | Custom / conditional: Apache- or BSD-based with extra conditions (branding, multi-tenant SaaS, derivatives). |
| Internal business use | Allowed under the license text |
| What to watch | Commercial use is allowed as a frontend and backend service without modifying the source. Developing and distributing a derivative work requires a commercial license from LobeHub. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
What hardware does LobeHub (LobeChat) need?
| Minimum | 2 vCPU · 4 GB RAM · 20 GB disk |
|---|---|
| Recommended | 4 vCPU · 8 GB RAM · 50 GB disk |
Docker Compose self-hosting figures. Storage needs grow with file uploads.
Source: lobehub.com/docs/self-hosting/platform/docker-compose
How much does it cost to host LobeHub (LobeChat) per month?
| Minimum spec | 2 vCPU · 4 GB RAM · 20 GB disk → CPX22 (2 vCPU, 4 GB, 80 GB disk) €19.99/mo |
|---|---|
| Recommended spec | 4 vCPU · 8 GB RAM · 50 GB disk → CPX32 (4 vCPU, 8 GB, 160 GB disk) €35.99/mo |
How we got this: we took the cheapest Hetzner Cloud Regular Performance (shared AMD vCPU) plan with at least the RAM and vCPU the project lists, using prices read from www.hetzner.com/cloud/regular-performance on 2026-10-22. "From" monthly price cap shown by Hetzner, excluding VAT. Prices vary by location. Covers the server only; it excludes LLM API usage, backups, extra storage, GPUs and your time. Disk is not matched; add a volume if you need more than the plan includes.
How to deploy LobeHub (LobeChat)
Method: Docker Compose (setup script)
mkdir lobehub && cd lobehub
bash <(curl -fsSL https://lobe.li/setup.sh) -l en
docker compose up -d From the official instructions: lobehub.com/docs/self-hosting/platform/docker-compose. Always check the source for the current version before you run it.
Known gotchas when self-hosting LobeHub (LobeChat)
Alternatives in Private ChatGPT-style chat
- Open WebUI Feature-rich self-hosted chat UI for Ollama and OpenAI-compatible APIs. Compare LobeHub (LobeChat) vs Open WebUI
- LibreChat Multi-provider ChatGPT-style interface with agents, file search and user management. Compare LibreChat vs LobeHub (LobeChat)
- Jan Offline desktop ChatGPT alternative that runs models on each employee's computer. Compare Jan vs LobeHub (LobeChat)
LobeHub (LobeChat) FAQ
How much RAM does LobeHub (LobeChat) need?
The official minimum is 2 vCPU · 4 GB RAM · 20 GB disk. The recommended spec is 4 vCPU · 8 GB RAM · 50 GB disk. Docker Compose self-hosting figures. Storage needs grow with file uploads.
How much does it cost to self-host LobeHub (LobeChat)?
The software is free to download. Based on the official minimum 2 vCPU · 4 GB RAM · 20 GB disk (recommended 4 vCPU · 8 GB RAM · 50 GB disk): That fits a Hetzner Cloud CPX22 server at about €19.99/month (server only, excl. VAT; €35.99/month for the recommended spec). That covers the server only, not LLM API usage, backups, extra storage or your time.
Is LobeHub (LobeChat) free for commercial use?
LobeHub (LobeChat) is licensed under LobeHub Community License (Apache-2.0 with conditions) (Custom / conditional). Internal business use is allowed under the license text. Commercial use is allowed as a frontend and backend service without modifying the source. Developing and distributing a derivative work requires a commercial license from LobeHub. This is a summary, not legal advice.
What are common problems when self-hosting LobeHub (LobeChat)?
Ports 3210, 9000, 9001, 8787 and 8788 must be free before deployment. The gateway keeps state in memory, so agent runs in progress are interrupted when it restarts. Distributing a modified version requires a commercial license.
Is LobeHub (LobeChat) still maintained?
Yes, it is actively developed. Last commit: Oct 22, 2026. Latest release: v2.2.20 (Oct 18, 2026). Checked Oct 22, 2026.
How do I install LobeHub (LobeChat)?
The official method is Docker Compose (setup script). The exact commands are in the "How to deploy" section above and in the official instructions: https://lobehub.com/docs/self-hosting/platform/docker-compose
What are self-hosted alternatives to LobeHub (LobeChat)?
Other apps in Private ChatGPT-style chat: Open WebUI, LibreChat, Jan.
Sources
- GitHub repository: github.com/lobehub/lobehub
- Official documentation, Hardware requirements, Deploy instructions, Gotcha 1, Gotcha 2: lobehub.com/docs/self-hosting/platform/docker-compose
- License text, Gotcha 3: github.com/lobehub/lobehub/blob/main/LICENSE
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-22. Spotted something out of date? Tell us.