Open-source AI workspace
How to use
LobeHub.
Using multiple AI providers in one workspace, building reusable assistants with files and knowledge, and operating a private multi-user LobeChat service with controlled extensions.
LobeHub is a Open-source AI workspace centered on LobeChat, with multi-provider chat, agents, knowledge bases, files, plugins, MCP, and self-hosting. Using multiple AI providers in one workspace, building reusable assistants with files and knowledge, and operating a private multi-user LobeChat service with controlled extensions. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.
AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.
Access & setup
Find, install, and sign in to LobeHub
Get into the official LobeHub experience with the right account and a setup you understand.
- 01
Start at https://lobehub.com/ and confirm the domain before entering account or payment information.
- 02
Availability: LobeHub offers hosted access and downloadable apps, while LobeChat can also be self-hosted through container or platform deployments with optional server database and authentication services.
- 03
A supported browser or app, model-provider credentials or a local model endpoint, and for self-hosting a secured domain, authentication, database, object storage, encrypted secrets, backups, monitoring, and update ownership.
- 04
Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.
- 05
Run one low-risk test task before connecting sensitive files, repositories, or workspace data.
- Use official download pages.
- Review permissions during setup.
- Keep installers and applications updated.
First session
Your first useful LobeHub session
Learn the interaction loop using a small task with a clear outcome.
- 01
Define users, deployment model, data classes, providers, model rights, authentication, storage, knowledge, tools, retention, availability, budget, and backup and recovery requirements.
- 02
Choose hosted or desktop access for individual use, or a database-backed self-hosted deployment with SSO, PostgreSQL and vector support, object storage, HTTPS, and restricted registration for teams.
- 03
Configure scoped provider credentials and an allowlisted model set, create one narrowly instructed assistant, and test chat, file, knowledge, sync, and tool behavior with non-sensitive data.
- 04
Review provider data paths, tenant isolation, retrieval quality, plugin and MCP permissions, traces, failures, cost, backups, and restore, then pin and canary updates with rollback.
- State the outcome before the background.
- Provide the real source material.
- Review the result before expanding the task.
Quality control
Check the quality of LobeHub output
Establish that an autonomous run did the right thing, not merely that it finished.
- 01
Define what the run should achieve and what it must never touch before granting it a single tool.
- 02
Read the full execution trace: which tools were called, with what arguments, and in what order.
- 03
Verify the side effects directly in the target system rather than trusting the agent's own report of success.
- 04
Confirm failures surfaced as failures — a silent retry loop or a swallowed error is more dangerous than a crash.
- 05
Re-run the same task and compare: an agent that behaves differently across identical runs is not yet production-ready.
- Verify side effects in the system of record, not in the agent's summary.
- Require human approval for any irreversible or outward-facing action.
- Log every tool call so a run can be reconstructed afterwards.
Privacy & permissions
Use LobeHub safely
Bound what an autonomous system can reach before you let it run unattended.
- 01
Enumerate every tool, credential, and system the agent can reach, and remove the ones it does not need.
- 02
Require explicit human approval for irreversible actions: sending, publishing, paying, deleting, or deploying.
- 03
Run against non-production data until behaviour is predictable across repeated runs.
- 04
Set hard limits on spend, iterations, and runtime so a failure loop cannot run unbounded.
- 05
Treat anything the agent reads from the web or a document as data, never as instructions it may follow.
- Self-hosting the interface does not make remote model, embedding, search, storage, sync, or plugin traffic local. A database deployment adds authentication, database, vector, object-storage, migration, backup, and patch responsibilities. Never expose an unauthenticated instance or provider key; isolate tenants and knowledge, vet plugins and MCP servers, restrict registration and networks, redact observability, and test restores before upgrades.
- Follow your organisation's approved-use policy.
- Never treat fluent output as authorization to act.
Core workflows
Step-by-step ways to use LobeHub for the work it does best.
Each workflow is a separate guide with its own steps and review checkpoints.
Operate the database edition with explicit identity, network, storage, secret, migration, backup, and tenant controls.
↗ 02 WorkflowBuild a governed LobeHub knowledge assistantCombine approved files with a narrow assistant and reviewed tools while making provider and extension data paths explicit.
↗Official references
Check the current product documentation.
Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.
- LobeHub downloads ↗
- LobeChat project ↗
- LobeChat Docker deployment ↗
- LobeChat server database deployment ↗