Fully Managed LibreChat
as a Service

Deploy LibreChat as a fully managed service starting at €9/mo. Get automated backups, SSL, updates, support and monitoring included.

LibreChat is an open-source AI chat platform — one interface for OpenAI, Anthropic, Google, Mistral, and local models — combining the convenience of ChatGPT with the data control of self-hosted infrastructure. Switch models mid-conversation, search past chats, run agents, and keep every prompt on infrastructure you control.

✓Free 7-day trial  ✓99.9% Uptime SLA  ✓No credit card  ✓Cancel anytime

✓Free 7-day trial  ✓99.9% Uptime SLA
✓No credit card  ✓Cancel anytime

LibreChat

LibreChat

STARTING AT

€9/month
Automated Backups
Monitoring
Automated Updates
Auto SSL

USAGE

Unlimited
Human Support
Custom Domains
Terminal Access
File Manager Access
Deploy in your region — 21 locations worldwide
GermanyFinlandNetherlandsUKSwedenUnited StatesCanadaSingaporeJapanAustraliaBrazilSouth Africa+9 more →
LibreChat Preview Image

ABOUT THE SOFTWARE

What is LibreChat

LibreChat is an open-source, self-hosted AI chat platform. It puts every major model — and your own local ones — behind a single, familiar interface, so a whole team can work with AI without sending prompts to a consumer product you don't control.

The project is MIT-licensed and built by Danny Avila. In November 2025, ClickHouse acquired LibreChat and brought the founder and core team in-house, while committing to keep the project open-source. It has passed 23 million Docker pulls and roughly 34,000 GitHub stars, with an active community of several thousand developers — the most-starred open-source AI chat project for over a year.

LibreChat connects to OpenAI, Anthropic, Google, Azure, AWS Bedrock, Mistral, Groq, and OpenRouter, plus any OpenAI-compatible endpoint — including local models through Ollama. Teams at companies such as Shopify and Daimler Truck run it internally for staff. Beyond chat, it supports AI agents, the Model Context Protocol, a code interpreter, file search over your documents, and multi-user sign-in with roles.

FEATURES

What LibreChat does

LibreChat is one interface for many models, with the tools a team needs around them: agents, file search, a code interpreter, and shared, searchable history. It behaves like the consumer chat apps people already know, while keeping models and data under your control.

Multi-provider model switching

Switch between OpenAI, Anthropic, Google, Mistral, Groq, and local Ollama models inside one conversation. Configure providers once; everyone gets the same picker.

AI agents

Build agents that call tools, read files, run code, and follow custom instructions. Share them across the team or scope them per user.

Model Context Protocol (MCP)

Connect MCP servers to give agents access to internal tools and data sources — the same open standard a growing set of AI clients now use.

Code interpreter and Artifacts

Run code in a sandbox and render React, HTML, and Mermaid diagrams inside the chat, so output is more than a wall of text.

File search (RAG)

Upload documents and let models answer from them. The vector store and RAG API handle embeddings and retrieval behind the scenes.

Conversation search

Full-text search across past chats with typo tolerance, powered by Meilisearch. Find that thread from three weeks ago in seconds.

Multi-user sign-in

Register users, set roles, and connect single sign-on (SAML, OIDC, LDAP). Run shared keys, or let each user supply their own.

Presets and prompts

Save model settings, system prompts, and parameters as reusable presets, so repeatable work starts the same way every time.

WHAT'S ALWAYS INCLUDED

Every app. Fully managed.
Nothing extra to pay for.

Every app on DANIAN ships with the same operational baseline. You do not choose a backup add-on or a monitoring tier. Hosting, patching, backups, SSL, and support are part of the €9, and they apply to LibreChat the same way they apply to everything else in the catalog.

Automatic updates and patches

Apps run the latest stable version. Security patches applied silently, with rollback if needed.

Daily off-site backups

Multiple daily backups in redundant off-site locations. One-click restore if anything goes wrong.

24/7 uptime monitoring

Continuous monitoring with instant alerting. We respond before you notice.

SSL, firewall, DDoS protection

Auto-renewing SSL, hardened firewall rules, DDoS mitigation on every deployment.

Performance and scaling

We monitor resource usage continuously. When your app needs more headroom, we flag it and upgrade with your explicit approval.

Dedicated engineering support

Real engineers by email and ticket. DNS, SMTP & migration help. All included in €9.

WHY MANAGED

Why teams pick managed LibreChat

In 2025 a US court ordered OpenAI to preserve ChatGPT logs — including deleted and temporary chats on consumer and Team accounts — and later to hand 20 million conversations to litigants. For teams handling client or product data, that was the push toward AI they actually control.

Self-hosting LibreChat looks like one container. A working production install is really four coordinated services: the app, a MongoDB database, a PostgreSQL vector store, and a separate RAG API for file search. Each needs its own secrets, persistence, memory budget, and update cadence — and they have to start in the right order to work at all.

The parts fail quietly. The search index drifts out of sync with MongoDB and has to be rebuilt before past chats are findable again. The vector and RAG containers eat real memory, so a 2 GB box that ran the demo stalls once a few people upload documents. And the encryption keys that protect stored API credentials — CREDS_KEY, CREDS_IV, and the JWT secrets — have to be generated correctly, or logins and saved keys break on the first restart.

We run all four services as one managed instance, wired together with private networking and daily off-site backups of your database and uploaded files. We generate and hold the encryption and session secrets so stored model keys and multi-user sign-in work on first login, size the RAG and vector containers for real document use, and re-sync search when it drifts — before you notice. You connect the models; we keep the stack running.

REVIEWS

Hear from customers ​like you​​​​​​​

Successful businesses and professionals around the world rely on DANIAN every day

USE CASES

Three teams who run LibreChat on DANIAN

These are the teams managed LibreChat fits: ones that want AI for everyone, without a per-seat bill or prompts leaving their control. Each runs one instance, picks the region near their people, and connects the models they already pay for.

12-PERSON SOFTWARE TEAM

One AI workspace, not a dozen seats

A development shop replaced individual ChatGPT subscriptions with a single instance in Germany. Engineers switch between Claude and GPT models per task, share agents wired to internal docs over MCP, and pay their own provider rates instead of $25 per head.

8-PERSON MARKETING AGENCY

A branded assistant that stays in-house

An agency runs LibreChat on a custom domain, with per-client presets and file search over each client's brand guidelines. Account managers draft and research in one place; nothing is sent to a consumer product, and roles keep each client's material separate.

RESEARCH GROUP

Local models for sensitive work

A research team points LibreChat at local models via Ollama for unpublished data, and at cloud APIs for everything else. Conversation search keeps a year of threads findable, and the whole group works from one instance in the region closest to them.

COMPARISON

Four ways to run LibreChat

ChatGPT for a team is priced per seat and runs on one vendor's models. The self-hosted paths give you control but hand you a five-service stack to operate. Managed LibreChat keeps the control and the model choice, at a flat price that doesn't grow with headcount.

Approach1 user5 users10 usersYour monthly opsWhat you're trading
ChatGPT Business$25/mo$125/mo$250/moNoneOne vendor's models; data retention set by the vendor; the bill grows with every seat.
Self-host on a VPS~$24/mo~$24/mo~$24/mo2–4 hrs + setupFive services to run, patch, secure, and back up yourself; database tuning past ~25 users.
Home server€60–110/mo€60–110/mo€60–110/mo2–4 hrs/moHardware, electricity, business internet, off-site backup; a GPU if you want local models.
DANIAN managed LibreChat€9/mo€9/mo€9/moNoneBring your own model keys or local models; we run the five-service stack and the backups.

LibreChat doesn't include the AI model. You connect your own provider keys, billed at cost — or point it at local models and pay nothing per token. The €9 covers the platform, hosting, and management. What you stop paying is the per-seat platform tax and single-vendor lock-in. * ChatGPT Business: $25/user/month billed monthly (two-seat minimum); model usage included. A single user would typically use ChatGPT Plus at $20/month. † Self-hosted paths: plus the model API usage you choose, or $0 with local models. ‡ Home server: plus €700–1,500 one-time for a business-grade mini-PC or tower with 32 GB RAM, amortised over three years.

BY INDUSTRY

LibreChat for specific industries

Different teams put different demands on an AI workspace — some need local models, some need strict separation between clients, some need many light users on one instance. Here is how managed LibreChat fits five of them.

Engineering teams care less about a chat box and more about access control and data handling. LibreChat lets you enforce single sign-on with OIDC or SAML, scope agents per team, and connect internal tools over the Model Context Protocol — so an assistant can read your docs without anyone pasting them into a consumer product. A common pattern: engineers run code review and debugging against Claude and GPT models, and answer questions over a repository through file search. We wire sign-on on request, hold the encryption keys that protect each stored provider credential, and keep the database backed up off-site daily. For a 12-person team, one €9 instance plus usage-billed API keys replaces roughly $300 a month in per-seat subscriptions, while keeping prompts on infrastructure you control.

Agencies juggle many clients and can't have one client's material bleeding into another's. LibreChat runs on your own domain with role-based access, per-client presets, and file search scoped to each client's brand guidelines and past work. Account managers draft copy, research, and summarize calls in one place; writers reuse saved prompts so a client's voice stays consistent across the team. Because billing is per app, an eight-person agency runs a single €9 instance instead of eight separate seats, and connects whichever models it already pays for. We set up the custom domain and SSL, configure roles so each client's files stay separate, and back the whole instance up daily — so a laptop lost on a train doesn't take a client's research with it.

Research groups often work with data they cannot send to a third-party API: unpublished results, interview transcripts, funder-restricted datasets. LibreChat handles both worlds. Point it at local models through Ollama for sensitive work, and at cloud providers for routine drafting and literature review. Many funders and institutions ask for a data-management plan describing where research data lives; running your own instance gives a clear, honest answer. A typical setup keeps a year or more of conversations searchable through full-text search, so a question explored last term is findable now. We provision the vector store and RAG API sized for document-heavy use, run local-model endpoints where you need them, and back up the database and uploads off-site every day — with no per-seat cost as the group grows or shrinks between terms.

Law firms and professional-services teams answer to client-confidentiality duties that most consumer AI tools sit awkwardly against. The 2025 court orders requiring a major provider to preserve and produce chat logs made the risk concrete. LibreChat keeps prompts and documents on infrastructure you control, with retention you set rather than a vendor's. Roles separate who can see what; file search lets a fee-earner summarize and query the documents on a matter without uploading them to a public product. We hold the encryption keys that protect stored model credentials, configure role-based access, and back up the database and files off-site daily. Billing per instance — not per fee-earner — means a small practice can give the whole team access for €9 plus the API usage it actually consumes, with conversations kept where the firm, not a third party, decides how long they live.

Support and operations teams have lots of people who each use AI a little — exactly the pattern per-seat pricing punishes. LibreChat puts everyone on one instance with shared agents and presets tuned to your tone and policies. Connect your knowledge base or helpdesk over the Model Context Protocol, and agents can draft replies, summarize long ticket threads, and answer from internal docs. Roles keep customer data visible only to the people who should see it. Because the price is per instance, a 20-person support team pays €9 plus usage rather than 20 separate subscriptions. We wire roles and connectors, keep the search index healthy so past tickets stay findable, and back the instance up off-site every day.

FAQ

Frequently asked questions

Three groups of questions: how LibreChat works on DANIAN, how to move onto it, and how billing and support work. If something here is unclear, chat with us and a person will answer.

Three groups: technical setup, migration, and how DANIAN works as a service.

01

Technical and configuration

Any of the major providers: OpenAI, Anthropic, Google, Azure, AWS Bedrock, Mistral, Groq, and OpenRouter, plus any OpenAI-compatible endpoint and local models through Ollama. You configure them once and everyone sees the same model picker, and you can switch between models inside a single conversation.
Yes. We can set any provider to user-provided, so each member enters their own key in the interface, or you can run shared keys at the instance level. We hold the encryption secrets, so stored keys are kept encrypted at rest rather than sitting in plain text.
Yes. Point LibreChat at a local Ollama instance and every model you have pulled appears in the picker. Prompts stay on your infrastructure and there is no per-token charge. We set up the local endpoint as part of onboarding.
Yes. The vector store and RAG API are part of the instance we run, so uploads are embedded and searchable. We size those containers for real document use, because the default 2 GB setup stalls once several people upload files at once.
Both are supported. You can build agents that run code, read files, and call tools, and connect Model Context Protocol servers to reach internal systems. Agents can be shared across the team or scoped to individuals.
Yes. Your instance runs on your own subdomain or domain with SSL handled for you, so people reach chat.yourcompany.com instead of a shared URL. We set up the DNS and certificate with you.

02

Migration and onboarding

21 datacenter locations across six continents. You choose the region at provisioning. Application data sits in the region you choose; pick whichever is closest to your users or matches your data-residency preference.
Yes. Request a region migration from the dashboard and we run the move in the background. The system emails you when the migration completes; total transfer time depends on data volume but typical instances finish in a few hours. There is no extra charge for a region change.
Yes. Full data export is available at any time, in a portable format you can bring to any infrastructure.
Most teams start fresh, because there is no export of a ChatGPT account that imports cleanly. You add your provider keys, set up users, and point people at the new URL. We handle the deployment and the model setup; you bring the keys.
Usually the same day for a standard instance. Custom domains, single sign-on, and local-model endpoints can add time depending on your DNS and identity provider. We tell you what is left before you go live.
Yes. Setting up providers, agents, MCP connectors, and sign-on is the kind of work we do on chat, not something we leave you to figure out from documentation.
Yes. Every app includes a 7-day free trial with no card. Activate LibreChat, connect a key, and use it with your team before you decide.
Your model provider keys, or a local-model setup, a domain if you want a custom one, and your identity provider details if you need single sign-on. We do the rest.

03

Billing, support, and platform

€9 covers everything we do for that app: hardware in the region you choose, daily off-site backups with one-click restore, automatic security patches and version upgrades, 24/7 monitoring, SSL and firewall, and engineering support on email and the ticket section in the client portal. There are no setup fees or hidden line items. For more info see our Pricing page.
If you decide to continue, we charge €9/app/month from day 8. If you don't, the trial ends and you can export your data. No card is required for the trial, and we never auto-charge you without explicit consent.
No. The €9/month is flat regardless of how many users log into your app. Add 5 users or 50; the price doesn't change.
24/7 email and ticket support, both staffed by engineers who run the systems. We handle DNS configuration, SMTP setup, app integrations, performance tuning, troubleshooting, and migration help. Response time is typically under an hour. There is no tier system — every customer gets the same support.
Yes. Cancel from the dashboard. We don't charge a cancellation fee, we don't lock data, and we will export your data to you on request before deletion. data to you on request before deletion.
Every customer instance is backed up daily to a separate region from the primary. We test restores. You can request a restore at any backup point within the retention window — usually 7 days for daily backups.
Your application data sits in the region you choose at provisioning — 21 datacenter locations across six continents. Account-level data (billing, account email, support ticket history) is processed centrally. Application data region is picked by you, per app.
99.9% uptime SLA on every app, every tenant. Service credits are documented at danian.co/service-level-agreement. The status page is located at status.danian.co.
When your tenant approaches the resource ceiling — the base tier holds 1 vCPU/RAM, 30 GB storage — we notify you. Resource upgrades happen with your explicit consent; we will not upgrade your tenant or charge you without it.
We wait. We don't suspend the app or delete your data on the first failed charge. We email you, you fix the card on file, and we continue.
Invoices can be downloaded from the billing dashboard in PDF the day each charge succeeds. EU VAT is added where applicable and the VAT-reverse-charge regime applies for VAT-registered businesses with a valid number.
150+ open-source apps across automation, team chat, file sync, analytics, AI, password management, email marketing, dev tools, project management, smart home, CMS, and federated social. See the full catalog →
Yes. Every instance comes with a web-based terminal and a file manager in your DANIAN management dashboard. Useful for managing your data and customizations.
Resources scale with your usage. If your app needs more vCPU, RAM, or storage, we add it — and we ask first before any change to your plan. €9 is the floor; resource-heavy workloads may price higher, but you'll always know in advance.
Yes. We have both a Partner program and an Affiliate program available. Anybody can sign up.
No contract. No minimum commitment. Cancel anytime from the dashboard with one click. The 7-day free trial requires no credit card. After the trial converts to paid, you can still cancel at any month without notice or penalty.

DEPLOY IN YOUR REGION

21 datacenter locations on six continents

Pick the region closest to your users.

United States, Germany, Finland, Singapore, Australia, Brazil, Canada, Netherlands, UK, Spain, Italy, France, Sweden, Malaysia, India, Japan, Mexico, Poland, South Korea, Chile, South Africa and more coming soon

Global Reach Map

Try managed LibreChat for 7 days

No card. Cancel from the dashboard.