# Ontheia

> Your Data. Your AI. Your Rules. — Ontheia is the self-hosted AI agent platform for organizations that cannot afford to send their data to external cloud services.

Ontheia solves a concrete problem: every request to a cloud AI (ChatGPT, Gemini, Claude via third-party services) sends your data to foreign servers — uncontrolled and often without a clear legal basis. Ontheia is the alternative: the same AI capabilities, but running exclusively on your own infrastructure. Your data never leaves your servers.

Ontheia runs on Docker, deploys in under 30 minutes, and connects any AI model (Anthropic Claude, OpenAI GPT, Google Gemini, local models via Ollama) to your tools and data via the MCP protocol.

## The Problem — why Ontheia exists

**Data leaking through the back door:** Every request to a cloud AI sends your data to foreign servers — uncontrolled, opaque.

**Vendor lock-in:** One provider change, one price hike, one updated ToS — and your AI stack collapses.

**Compliance risk:** Personal data in US cloud services is legally precarious in the EU. That costs nerves — and potentially money.

## What Ontheia is — Core Capabilities

**Self-hosted:** Runs on your own infrastructure. Docker-based, easy to deploy. On-premise or VPS — your choice.

**Multi-provider:** Claude, ChatGPT, Grok, Gemini, Ollama — you choose the model. No lock-in. Define per agent which model sees which data.

**Multi-User:** Role-based access control, teams, and projects — Ontheia is built for organizations from the ground up.

**Workflow Engine:** Visual automation pipelines. Complex agent logic without code. Agents execute multi-step tasks autonomously.

**Long-term Memory (RAG):** Built-in RAG with pgvector. Your agents remember and access your company knowledge. Documents, manuals, past projects — all searchable.

**Agent-to-Agent:** Agents communicate directly with each other. Complex tasks can be split and coordinated between agents.

## How it works

Ontheia sits between your data and the AI models:

- **Your Servers** — Linux, Docker, on-premise or VPS. Your data, your control.
- **Ontheia** — Agents & Workflows, Multi-Provider Router, Memory/RAG, Multi-User & RBAC.
- **Your Models** — Claude, GPT, Gemini, Ollama (local). No vendor lock-in.

Sensitive company knowledge stays on your servers. Routine tasks use the best available cloud. Data sovereignty without productivity loss.

## Who uses Ontheia — Industries and Use Cases

### Medicine & Law — Protecting professional secrecy
Doctors document findings, search medical literature via RAG, and prepare correspondence. Lawyers review contracts and research case law. Patient and client data never leaves your own infrastructure. Ontheia is the only AI platform that technically enforces medical confidentiality and attorney-client privilege — because the data never leaves the office.

**Suitable for:** Lawyers, notaries, doctors, therapists, tax advisors, auditors — all professions with a legal duty of confidentiality.

### Banking & Finance — Compliance without compromise
Automatically analyze loan documents, generate regulatory reports, and monitor transactions for anomalies. Banks are subject to strict financial regulation and banking secrecy — customer data in US cloud is not an option. Ontheia enables AI-assisted financial analysis that meets regulatory requirements.

**Suitable for:** Banks, savings banks, credit institutions, asset managers, financial advisors.

### Public Administration — Citizen services on your own servers
Automatically classify and respond to citizen inquiries, process forms, maintain internal knowledge bases. Faster citizen service, less burden on staff — with full sovereignty over all administrative data. For public authorities, on-premise is not optional — it is required by law.

**Suitable for:** City administrations, districts, federal agencies, public institutions, schools, universities.

### Industry & Production — Intelligent production monitoring
Analyze machine and sensor data in real time, detect anomalies, predict maintenance needs. Produce more efficiently, reduce downtime. The knowledge of your plant works for you. Trade secrets and OT security remain protected.

**Suitable for:** Manufacturing companies, mechanical engineering, automotive, chemical, pharmaceutical industry.

### Architecture & Engineering — Structured access to project knowledge
Automatically maintain planning documents, search standards and regulations via RAG, generate technical reports. Every project enriches the knowledge base. Over time, accumulated know-how works for every new assignment.

**Suitable for:** Architecture firms, engineering offices, planning offices, construction companies.

### Trades & Small Business — Automating day-to-day operations
Capture and track orders, prepare supplier requests, automatically inform customers about delivery dates, create correspondence and quotes. More time for the actual work.

**Suitable for:** Tradespeople, service providers, SMEs, small businesses with employees.

## Data Sovereignty & GDPR

Cloud AI is powerful. But it processes everything you give it — including what was never meant for third parties. Ontheia gives you back control: define per agent which model sees which data. Sensitive company knowledge stays on your servers. Routine tasks use the best available cloud.

Ontheia is the only AI orchestration platform that is simultaneously self-hosted, multi-provider, MCP-native, and GDPR-compliant by architecture. For EU companies, this is not a nice-to-have — it is a legal requirement.

## Open Source

Ontheia is licensed under AGPL-3.0. Open source. For everyone. The code is open on GitHub, development is transparent, the community is welcome. A commercial license is available for use cases that require it.

## Links

- [Website](https://ontheia.ai): Product overview, use cases, GDPR
- [Documentation](https://docs.ontheia.ai): Technical documentation, installation, admin guide
- [GitHub](https://github.com/Ontheia/ontheia): Source code, issues, contributions
- [Installation](https://docs.ontheia.ai/en/getting-started/02_installation): Get started in under 30 minutes
- [Compatible AI Providers](https://docs.ontheia.ai/en/getting-started/04_compatible-providers): Ollama, llama.cpp, Claude, GPT, Gemini and more