WZ-IT runs AnythingLLM as a dedicated instance in data centres in Germany, Switzerland or Austria, with updates, daily backups, 24/7 monitoring and a personal contact. On request, we also install AnythingLLM in your cloud or on premises.
AnythingLLM is a fully self-hostable AI document chat platform that enables businesses to privately chat with their documents. As an all-in-one desktop & Docker AI application, AnythingLLM offers built-in RAG functionality, AI agents, a no-code agent builder, and much more.
AnythingLLM can connect local and remote LLM providers as well as different vector stores and provides team workspaces. Which data leaves the environment depends on the selected model, embedding and integration services.
Query document content through a chat interface. Quality and source grounding depend on extraction, chunking, indexing, retrieval and the selected model.
RAG (Retrieval-Augmented Generation)
RAG retrieves suitable document passages for the model response. Indexing, permissions, retrieval and source display are tested for the concrete corpus.
Multi-LLM Support
Supports multiple LLM providers: Ollama (local), OpenAI, Anthropic Claude, Google Gemini, Azure OpenAI, LM Studio, and many more. Flexibly switch between providers based on requirements.
Controllable data flows
With an entirely local configuration, documents, embeddings and model requests can remain in your environment. When remote LLM or embedding providers are used, the content sent to them is processed externally.
Multi-User Workspaces
Create separate workspaces for different teams, projects, or use cases. Each workspace can have its own documents, LLM configurations, and permissions.
Intelligent Document Management
Processes common document formats into chunks and embeddings. Supported formats and result quality depend on version, parser and document structure.
Enterprise Security
Access rules and connections to existing identity services are combined with network, transport and storage encryption in the operating environment. Available features depend on version and edition.
Open source
The publicly available source code supports technical review and adaptation. Dependencies, connected models and external services are included in the security assessment.
Self-Hosted or Managed
Run AnythingLLM on-premise, in your cloud, or use our managed hosting. The deployment and connected model services are configured around your privacy and compliance requirements.
Infrastructure, integration and operations
AnythingLLM as part of your infrastructure
We do more than provide an application. WZ-IT designs the technical architecture, integrates network and identity, operates the agreed scope and develops integrations when the standard product is not enough.
Architecture and migration
Sizing, target environment, data transfer, cutover and recovery are resolved before production operations.
On-Premise
In your data center: Installation on bare-metal, VM or Docker · Integration with existing Active Directory/LDAP
Installation in your cloud
In your own cloud account, for example with AWS, Azure, GCP or Hetzner · Terraform/IaC setup (optional) · Kubernetes or Docker Compose · Capacity and scaling design
Enterprise Setup
Advanced architecture after technical and licence assessment: HA and recovery design where supported by the application and edition · Logging according to feature set and edition · Custom security policies
Network and identity
SSO, secure access, internal systems and existing security components are integrated appropriately.
VPN Access
WireGuard, NetBird, Tailscale, Headscale, OpenVPN, Cloudflare Tunnel · Easy client setup for all devices
SSO Integration
Directly or through an upstream identity layer
Multi-Factor Auth
Depends on application, edition and identity provider
Firewall & Hardening
Fail2Ban, Rate Limiting, IP Whitelisting
Monitoring and service level
Updates, backups, technical monitoring and response paths follow a transparent operational scope.
24/7 proactive monitoring
Updates and patches
Regular updates, CVE monitoring and prioritised patches for critical vulnerabilities
Daily backup with 7-day retention
Personal technical contact
Integration and development
APIs, automation and custom extensions can be delivered beyond basic deployment.
Chat & Query API
Integration of the chatbot into your existing software (intranet, support tool). Your app sends the question, AnythingLLM delivers the answer incl. citations.
Custom Data Connectors
Standard scrapers not enough? We write scripts that extract data from proprietary SQL databases or internal wikis, clean it, and load it into the vector store.
Agent Skills
We give the AI 'hands'. Development of tool definitions allowing the LLM to execute API calls (e.g., 'Book Room X' -> API call to calendar).
Full-service installation with no hidden costs
What the AnythingLLM setup includes
Complete installation & configuration
SSL certificate & reverse proxy setup
Backup strategy & disaster recovery
Performance optimization & tuning
Security hardening following OWASP
Monitoring & logging setup
Documentation & best practices
Administrator training (remote)
30 days email support included
Dedicated contact person
Optional integration: LDAP/AD, SSO, MFA
Update strategy & patch management setup
The exact scope depends on the application, edition, infrastructure and criticality. Vendor licences and non-standard components are quoted separately.
Use Cases
Using AnythingLLM in your organisation
AI-powered Document Chat
Chat with your documents and receive precise answers based on your own data using RAG technology
Knowledge Management
Centralize company knowledge in workspaces and make it searchable and usable for your entire team through AI
Private AI for Enterprises
Privacy-focused AI solution without data transfer to third parties - ideal for regulated industries and privacy-critical applications
Team Collaboration with AI
Multi-user support with workspace management, granular permissions and role-based access control for efficient teamwork
Flexible LLM Selection
Use local models (Ollama, LM Studio) or cloud-based LLMs (OpenAI, Azure, Anthropic) according to your requirements
Data Sovereignty & Compliance
Control over data location and access and AI models for healthcare, finance, government agencies and other regulated industries
Concrete Use Cases
AnythingLLM Development & Integration
AnythingLLM is the operating system for your private documents. We extend it so it reads documents and actively intervenes in your processes.
L1 Support Automation
Problem
Support is overloaded with recurring questions about manuals.
Solution
Embedding an AnythingLLM bot in the helpdesk. It immediately suggests relevant passages from technical docs to the agent based on the customer question.
Cronjob scripts that detect changes in Sharepoint/Confluence nightly and incrementally update the vector index.
Managed Hosting & Operations
How much does AnythingLLM hosting cost?
Compute, applications, storage and response are shown separately. You can see what ongoing operations include and which requirements need a technical assessment.
Starter workload from€99.90/ month · cancel monthlyWith a minimum term: 10% reduction on operations and hosting with 6 months, 20% with 12 months, payment monthly, half-yearly or yearly
AnythingLLM hosting in Germany: GDPR-compliant operations
One managed standard application included
.de domain included or your own domain or subdomain via CNAME
Choice of location: Germany (ISO 27001, BSI C5), Switzerland (ISO 27001) or Austria (ISO 27001), each within the scope of the data centre operator
Confidentiality agreement under Section 203 German Criminal Code (StGB) available on request (location Germany) New
Confidential compute VM optional, price on request New
99.9 % standard availability per month
Regular updates, CVE monitoring and prioritised patches for critical vulnerabilities
Central logs with immutable retention
Daily backup with 7-day retention
5 TB outbound traffic per workload and month
24/7 proactive monitoring
Five service levels, 24/7 P1 response with Production or Critical
Five service levels for different operating requirements
Response target = initial technical response to critical incidents (P1) · Price and flexible operations allowance per customer environment and month · Hourly rate for additional work
Response within service hours24/7 on-call for P1
Essential
Next business dayby end of dayInitial technical response to critical incidents (P1) by the end of the next business day
Mon to Fri, 8 to 17 CET
includedin the base operations price
no allowance
Hourly rate
5% below standard
regular service hours
€114
outsideoutside regular service hours
€228
For less time-critical systems, staging and internal applications.
Business
Popular
4 hwithin service hoursInitial technical response to critical incidents (P1) within 4 service hours
Mon to Fri, 8 to 18 CET
+€99.90
0.5 h allowance
Hourly rate
10% below standard
regular service hours
€108
outsideoutside regular service hours
€216
For production systems without contractual night and weekend on-call coverage.
Priority
1 hwithin service hoursInitial technical response to critical incidents (P1) within 1 service hour
Mon to Fri, 8 to 18 CET
+€199.90
1 h allowance
Hourly rate
15% below standard
regular service hours
€102
outsideoutside regular service hours
€204
For business-critical systems requiring a fast response during the service window.
Production
60 minnights and weekends includedInitial technical response to critical incidents (P1) within 60 minutes, 24/7
P1 around the clock
+€349.90
1 h allowance
Hourly rate
20% below standard
regular service hours
€96
outsideoutside regular service hours
€192
24/7 P1 on-call coverage for business-critical production environments.
Critical
after audit
30 minnights and weekends includedInitial technical response to critical incidents (P1) within 30 minutes, 24/7
P1 around the clock
+€549.90
2 h allowance
Hourly rate
25% below standard
regular service hours
€90
outsideoutside regular service hours
€180
Available after audit, runbook and capacity approval.
Business, Priority, Production and Critical include the first covered workload in a customer environment. Further covered workloads cost €29.90, €39.90, €49.90 and €59.90 per month respectively. For monitoring-only servers, we notify within the level's window for €14.90, €19.90, €24.90 and €29.90 per server and month respectively; without a service level, during service hours.
The flexible operations allowance applies to planned work during regular service hours and expires at month end. Operations, monitoring, backups, maintenance and updates within the agreed scope do not reduce it. Additional work beyond the agreed operations and the allowance, as well as further incident work, is billed at the hourly rate of the service level of the affected environment. The standard rate applies to commissioned work without a service level. Hour packages and fixed prices have their own prices. All prices are net and exclude statutory VAT. The offers are addressed to businesses.
Integrate AnythingLLM into your infrastructure with clear controls
AI applications need controlled model access, knowledge sources, permissions and observability in addition to the user interface. We design these data flows as one coherent stack.
Users and connected applications
Teams, business applications and API clients use defined interfaces and endpoints.
Secure access
TLS, firewall rules, reverse proxies or private network paths are designed around the platform's exposure.
Identity and permissions
Local accounts, SSO, directories, service accounts and emergency access are connected through clear roles.
AnythingLLM platform
Application logic, model access, roles and approved capabilities run in a controlled environment.
Models and compute
Local or external models, GPU/CPU resources, routing, limits and cost controls.
Knowledge and data
Documents, databases, vector search and traceable data paths for RAG and search.
Tools and observability
Reviewed tools, APIs, logging, metrics and technical quality controls.
Models, extensions and data sources are not enabled indiscriminately. Permissions, data exposure, cost and professional oversight are assessed per use case.
Powered by WZ-IT
Local AI server or custom GPU infrastructure
The AI Cube covers the compact entry point. For larger models, rackmount or high concurrency, we design custom GPU systems.
This page covers installation and the agreed platform operations for AnythingLLM. Custom code, the access layer and special confidentiality requirements remain clearly separated responsibilities that can be added when needed.
AnythingLLM Hosting with WZ-IT starts at €99.90 net per month. It includes a dedicated size XS instance (2 vCPU, 2 GB RAM, 40 GB NVMe SSD), updates, daily backups with 7 days of retention, 24/7 monitoring, 5 TB of outbound traffic and a first response to critical incidents by the end of the next business day. Larger instances and higher service levels cost extra; the configurator shows the total price.
The entry level is a dedicated size XS instance with 2 vCPU, 2 GB RAM, 40 GB NVMe SSD for €99.90; it suits lightweight applications as well as test and development environments. Size S with 2 vCPU, 4 GB RAM, 80 GB NVMe SSD costs €129.90. We check which size AnythingLLM needs in production before provisioning. Size M (4 vCPU, 8 GB RAM, 80 GB NVMe SSD) costs an extra €29.90 excl. VAT, L (8 vCPU, 16 GB RAM, 80 GB NVMe SSD) an extra €89.90 excl. VAT and XL (16 vCPU, 32 GB RAM, 80 GB NVMe SSD) an extra €199.90 excl. VAT, each per month. Additional storage costs €4.99 excl. VAT per 50 GB and month.
No. WZ-IT does not limit the number of users. How many users can work smoothly at the same time depends on usage and the chosen instance size XS to XL.
AnythingLLM Hosting can be cancelled monthly, with no minimum term and 30 days' notice to the end of the month. With a minimum term: 10% reduction on operations and hosting with 6 months, 20% with 12 months, payment monthly, half-yearly or yearly.
Germany, Switzerland and Austria are available at the same prices. All three locations are data centres without US clouds that are ISO 27001 certified within the scope of the respective data centre operator; in Germany we additionally operate with a German provider whose data centres are BSI C5 attested. A confidentiality agreement under Section 203 German Criminal Code (StGB) is also available for app hosting on request, at the German location only; the separate Section 203 Managed Cloud for professional-secrecy holders is available in Germany only.
Yes. Besides Germany, Switzerland and Austria are available as locations, at the same prices in euros. The operator of the data centre in Switzerland is certified to ISO 27001, ISO 9001, ISO 14001 and ISO 50001 and sources electricity from renewable sources; the data centre in Austria is ISO 27001 certified. State the preferred location in your request; it is recorded in the proposal.
We typically provide a production instance within a few business days after signing. For a trial, we set up a test instance, usually on the next business day; it runs free of charge for 7 days and without payment details.
Yes. One .de domain is included with every hosting plan. Alternatively, connect your own domain or subdomain with a CNAME record.
WZ-IT moved our studio infrastructure from decentralised individual devices to a central platform: every site is securely connected via VPN, new devices are onboarded automatically and an entire site is provisioned from a template, without manual steps on location. What impressed me most is the breadth and depth of their knowledge: Timo and Robin are not a typical IT provider who sets up a server and leaves. The two of them think their way into highly complex infrastructure and software topics, work through every requirement we put in front of them, and build networking, provisioning and operations so that everything fits together in the end. WZ-IT is an excellent partner for complex software, network and architecture projects.
Steve KirchnerManaging Director, nextGYM GmbHView project
International
Built in Germany's Ruhr Valley. Running worldwide.
WZ-IT designs, develops and operates infrastructure and software for clients in Germany and internationally. We deliver projects remotely and continue supporting them in ongoing operations after go-live.
