Tools we use

Last updated: 27 March 2026

This is a full record of every tool and service that runs Klai — from infrastructure to the open source libraries our code is built with. Some are sub-processors under GDPR: they handle personal data on your behalf and are covered by our DPA. Others are open source software we run on our own infrastructure, where no data leaves our servers. We note the difference.

The GDPR-specific sub-processor list is at /docs/legal/sub-processors.

Hosting & networking

ToolWhat it doesLocationSub-processor
Hetzner Online GmbHGerman hosting provider. Our servers run in their Finnish data center. Hosts all Klai data. DPA accepted 7 March 2026. See sub-processor detail.Finland (EU)Yes
Hetzner DNSDNS provider for getklai.com. Manages DNS records only. No customer data is processed.Germany (EU)No
Let’s EncryptFree, automated TLS certificate authority. Issues our HTTPS certificates via the ACME protocol. No customer data is processed.USANo
Cloud86Dutch hosting and email provider. Manages Klai’s business email and acts as SMTP relay for invitation emails sent by Klai. Processes recipient email addresses in transit. DPA not yet signed.Netherlands (EU)Yes

Platform & orchestration

These run on our own Hetzner servers. No customer data leaves our infrastructure.

ToolWhat it does
DockerOpen source container runtime. All Klai services run as Docker containers on our own infrastructure.
CoolifyOpen source deployment platform. We use it to manage containers, updates, and services on our own infrastructure.
CaddyOpen source reverse proxy and web server. Handles HTTPS termination and routes traffic between internal services.
ZitadelOpen source identity provider. Manages user accounts, authentication (OIDC), and access control. Stores account credentials and session data on our own infrastructure.
SOPS + ageOpen source secrets management. All infrastructure secrets (API keys, passwords) are encrypted with age and stored as SOPS-encrypted files in our private Git repository.
Fail2banOpen source intrusion prevention. Monitors server logs and blocks IP addresses that show signs of abuse.

Databases & storage

All databases run on our own Hetzner servers. Customer data stays in our infrastructure.

ToolWhat it does
PostgreSQL (with pgvector)Open source relational database. Stores user accounts, tenant configuration, portal data, and the portal API state. The pgvector extension adds vector search support.
MongoDBOpen source document database. Stores chat conversations per tenant. Each tenant has a separate database.
RedisOpen source in-memory data store. Used for caching, session management, and message queuing.
RabbitMQOpen source message broker. Used internally by Firecrawl to queue web scraping jobs.
MeilisearchOpen source full-text search engine. Indexes chat messages so users can search their conversation history.
QdrantOpen source vector database. Stores document embeddings for semantic search over uploaded documents.
FalkorDBOpen source graph database. Stores the knowledge graph used for context-aware retrieval across the knowledge base. Runs on our own infrastructure.

Monitoring & observability

All monitoring runs on our own infrastructure. Log and metric data stays on our servers.

ToolWhat it does
VictoriaMetricsOpen source time series database. Stores operational metrics (CPU, memory, request rates) with 30-day retention.
VictoriaLogsOpen source log storage. Stores container logs with 30-day retention. Logs may contain IP addresses and request metadata.
GrafanaOpen source monitoring dashboard. Visualises metrics and logs from VictoriaMetrics and VictoriaLogs. Access restricted to Klai staff via authentication.
Grafana AlloyOpen source metrics and log collector. Forwards Docker container logs and node metrics to VictoriaMetrics and VictoriaLogs.
cAdvisorOpen source container resource monitor. Collects CPU, memory, and network metrics per container.
GlitchTipOpen source error tracking (Sentry-compatible). Captures application errors to help us diagnose and fix problems. Runs on our own infrastructure.
Uptime KumaOpen source uptime monitor. Checks whether our services are running and alerts us when they are not.
UmamiOpen source privacy-friendly website analytics. Cookieless, GDPR-compliant by default. Tracks pageviews and custom events on getklai.com. No personal data is collected. Runs on our own infrastructure.

AI product

ToolWhat it does
LibreChatOpen source AI chat interface. This is the product interface customers use to interact with AI models. Conversation data is stored on our own infrastructure and does not leave our servers.

AI inference & models

ToolWhat it doesLocationSub-processor
LiteLLMOpen source AI gateway. Routes requests between our local models (Ollama) and external inference (Mistral). Runs on our own infrastructure.Klai infrastructureNo
OllamaOpen source software for running language models locally. We use it to serve AI models on our own infrastructure. Nothing leaves our servers.Klai infrastructureNo
Mistral AI SASFrench AI company whose models we use for inference. Receives only the API call content: the query and any uploaded documents. No account data. Not retained. Not used for training. DPA accepted 7 March 2026. See sub-processor detail.France (EU)Yes
Hugging Face TEI (Text Embeddings Inference)Open source inference server for embedding models. We run it locally with the BAAI/bge-m3 model to generate vector embeddings from documents. Nothing leaves our servers.Klai infrastructureNo
InfinityOpen source reranking server. We run it locally with the BAAI/bge-reranker-v2-m3 model to rerank search results. Nothing leaves our servers.Klai infrastructureNo
SearXNGOpen source privacy-respecting metasearch engine. Powers web search in the chat interface and the research feature. Runs entirely on our own infrastructure — queries are not sent to commercial search APIs.Klai infrastructureNo
VexaOpen source meeting bot manager. Enables the meeting transcription feature by joining video calls on behalf of the user. Runs on our own infrastructure. Meeting audio is processed locally via Whisper.Klai infrastructureNo

Document & audio processing

These run on our own servers. Uploaded files and audio recordings are processed locally and are never sent to external services.

ToolWhat it does
WhisperOpen source speech-to-text model developed by OpenAI. Powers the transcription feature. Audio is processed entirely on our own infrastructure.
doclingOpen source document conversion tool. Converts uploaded PDF and DOCX files to text so AI models can read them. Runs on our own infrastructure.
FirecrawlOpen source web scraper. When you use web search in the chat interface, Firecrawl fetches and extracts the full text of web pages so the AI model can read them. Runs entirely on our own infrastructure.

Business tools

ToolWhat it doesSub-processor
FiderOpen source feature voting and roadmap software. If you submit a request or vote, your email is stored on our own infrastructure and stays safe with us.No
TwentyOpen source CRM. We use it to manage customer relationships. Runs on our servers. Your contact details stay with us.No

Payments

ToolWhat it doesLocationSub-processor
Moneybird B.V.Dutch accounting and billing platform. Handles subscriptions, invoicing, and SEPA direct debit. Processes billing contact data including IBAN, KvK, and VAT number. DPA signed 7 March 2026 (v1.2). See sub-processor detail.Netherlands (EU)Yes

Development & source control

ToolWhat it does
GitHubSource code hosting and CI/CD. Stores Klai’s application code under the GetKlai organisation. No customer data is stored here.
GiteaOpen source self-hosted Git service. Used as the backend for the knowledge base — documents you publish via the knowledge base editor are stored here as Git-managed files on our own infrastructure.
uvOpen source Python package manager and project tool. Used to manage backend dependencies and virtual environments.
ruffOpen source Python linter and formatter. Enforces code style and catches common errors in backend code.
pyrightOpen source Python type checker developed by Microsoft. Validates type correctness in backend code.
pre-commitOpen source git hook framework. Runs ruff, pyright, and pip-audit automatically before each commit.
pip-auditOpen source Python dependency vulnerability scanner. Checks for known CVEs in backend dependencies before each commit.
TrivyOpen source container security scanner. Scans Docker images for known CVEs during CI/CD and reports results to the GitHub Security tab. No customer data is processed.

Frontend libraries

The portal and website are built with the following open source libraries.

LibraryWhat it does
ReactOpen source UI library. Powers the klai-portal customer interface.
ViteOpen source frontend build tool. Bundles and serves the portal frontend.
TanStack RouterOpen source type-safe client-side router for the portal.
TanStack QueryOpen source data fetching and caching library for the portal.
TanStack TableOpen source headless table library for the portal.
Tailwind CSSOpen source utility-first CSS framework. Used across portal and website.
MantineOpen source React component library. Used for UI primitives in the portal.
Radix UIOpen source headless UI component library. Used for accessible interactive components in the portal.
BlockNoteOpen source rich text editor. Powers the knowledge base editor in the portal.
Paraglide JSOpen source compiler-based i18n library. Handles Dutch/English translations in the portal with zero runtime overhead.
Lucide ReactOpen source icon library. All icons used in the portal and website come from here.
AstroOpen source web framework. Powers the getklai.com website.
KeystaticOpen source Git-based CMS. Used to manage website content (blog posts, pages) without a database.
Next.jsOpen source React framework. Powers the klai-docs documentation site.

Backend libraries

The portal API (FastAPI, Python) is built with the following open source libraries.

LibraryWhat it does
FastAPIOpen source Python web framework. The entire klai-portal API is built on it.
UvicornOpen source ASGI server. Runs the FastAPI application in production.
SQLAlchemyOpen source Python ORM. Handles all database queries and schema management.
AlembicOpen source database migration tool. Manages PostgreSQL schema changes.
PydanticOpen source data validation library. Validates and serialises all API request and response data.
asyncpgOpen source async PostgreSQL driver. Powers database connections from the portal API.
cryptographyOpen source Python cryptography library. Used for encryption operations in the portal API.

This document is published under CC BY 4.0. You are free to adapt it for your own organisation. Credit: Klai B.V.