🇩🇪 Made in Germany · GDPR-native · EU-hosted
AI that respects
your data.
A privacy-first fractal AI mesh. Same binary at every layer. Escalation gated by PII redaction and GDPR consent. Open source at the core.
Try it live → /edge/chat Real qwen2.5:1.5b on Hetzner EU. No signup. 5 sec.
Built for regulated industries. Engineered for data sovereignty.
The Problem

Cloud AI leaks your most sensitive data.

⚠️

Data leaves your network

Every ChatGPT query, every Claude prompt, every Copilot completion sends your business data to US servers. For regulated industries, this is non-negotiable risk.

📋

GDPR + EU AI Act

Europe's regulatory framework makes sending personal data to cloud LLMs legally perilous. Article 30 requires full audit trails of every data transfer — something SaaS AI tools can't provide.

🔒

Vendor lock-in & trust

Third-party AI providers change terms, raise prices, and train on your data. Sovereign AI means you own the stack — inference, memory, audit logs.

Two Products, One Mission

Choose your deployment model.

Both products solve the same problem — privacy-first AI — through different architectures. Pick the one that fits your scale, compliance needs, and team.

Privacy-First

Magi Edge

AI that never leaves your network.
A fractal node protocol. Every node is the same binary — your environment variable decides if it's a laptop, a department server, or an enterprise root. Runs locally on Ollama. Escalates to the parent only when needed — always with PII stripped first.
For CISOs, DPOs, and regulated industries (finance, healthcare, legal) who cannot send data to cloud AI providers.
  • Fractal node mesh — same binary at every layer
  • PII scan + redaction on every escalation
  • Local-first: Ollama 7B on your laptop
  • GDPR consent gate before any data leaves
  • Zero cloud dependencies
  • MIT License — fully open, fully inspectable
421
Tests
38
Endpoints
4
Backends
0
Cloud Deps
Enterprise

Magi Cloud

Full-featured enterprise AI platform.
Everything a procurement officer needs to check boxes against: dashboard, billing, SSO, SCIM provisioning, audit trails, compliance reports, plugin marketplace. 324 API endpoints behind a 74-page React dashboard. Deploy on-prem or in your VPC.
For CTOs, IT leaders, and enterprise teams deploying AI at scale with full compliance machinery.
  • 324 API endpoints, 74-page React dashboard
  • 9 specialist AI agents with auto-routing
  • SOC 2 Type II, HIPAA, EU AI Act ready
  • Stripe billing with 4-tier plans + OEM
  • SAML SSO, SCIM, MFA/TOTP
  • Plugin marketplace with 29 signed plugins
4.7K
Tests
324
Endpoints
9
Agents
50+
DB Tables
Use Cases

Built for industries where data matters.

These are the scenarios where cloud AI is off the table — and where Magi Elior thrives.

Finance & Banking

Client data that can't leave the bank.

Wealth managers analyzing client portfolios. Compliance officers reviewing transactions. Risk teams summarizing filings. All with PII that legally cannot be sent to third-party AI.

Solution: Magi Edge runs on the analyst's workstation. PII is stripped before any cross-node query. BaFin and MaRisk compliant by design.
Healthcare

Patient records, never in the cloud.

Clinicians summarizing patient charts. Medical research across cohort data. Insurance claims analysis with diagnosis codes. All HIPAA and EU patient data protection territory.

Solution: Magi Cloud deployed on-prem in the hospital. Audit trail for every inference. Medical PII redaction by default.
Legal

Client privilege, protected by architecture.

Law firms reviewing contracts with client names. M&A teams summarizing deal documents. Litigation support with case strategy.

Solution: Magi Edge on every lawyer's laptop. Documents never leave the firm's perimeter. Client-privilege-aware escalation gates.
Public Sector

Sovereign AI for governments.

Ministries processing citizen data. Defense organizations analyzing intelligence. Regulators reviewing filings. All with strict data-residency requirements.

Solution: Full on-prem deployment. No external dependencies. MIT-licensed core you can audit end-to-end.
How It Works

The Fractal Mesh

Magi Edge's key insight: topology and identity are the same thing. One binary. One environment variable. Four roles.
Layer 0: ROOT         magi-elior.ai — 70B models, final fallback
  ↑ anonymized escalation (PII already stripped)
Layer 1: ENTERPRISE   your on-prem server — 32B models
  ↑ PII stripped, consent verified
Layer 2: DEPARTMENT   team server — 13B models (optional)
  ↑ first escalation target
Layer 3: EMPLOYEE     your laptop — 7B via Ollama

CapabilityVector (6D) decides at each layer:
Can I handle this locally? Yes → stay. No → escalate.

Cosine similarity against required-capability vector.
Escalation gated by: PII scan → consent check → audit log.
Raw data never leaves your device. Ever.
🇩🇪 Made in Germany

Engineered for European data sovereignty.

Built in Berlin. Hosted on EU infrastructure (Hetzner, Nürnberg). Open source at the core. Designed from day one around GDPR, the EU AI Act, and the regulatory reality of European business.

🇪🇺
EU-hosted infrastructure (Hetzner Nürnberg)
GDPR
Article 6, 7, 15, 17, 20, 30 compliant by architecture
MIT
Edge is fully open — inspect, fork, self-host
5K+
Automated tests across both products
Decision Helper

Edge vs Cloud

DimensionMagi EdgeMagi Cloud
ArchitectureFractal mesh (N nodes)Monolith (single deploy)
Installpip install + OllamaDocker Compose stack
InferenceOllama-first (local)vLLM / LM Studio / HuggingFace
Privacy modelPII-gate on every hopOn-prem deployment
AuthJWT + bcrypt + mTLSSSO + SAML + SCIM + MFA
ComplianceGDPR (consent gate)SOC 2, HIPAA, EU AI Act
AgentsReAct engine + tools9 specialist agents
BillingStripe, 4 tiers, OEM
FrontendMinimal chat UI74-page React dashboard
Plugin systemLocal plugins (MIT)Marketplace with 29 signed plugins
LicenseMITBUSL-1.1
Best forData sovereignty, edge deploymentEnterprise AI at scale
Questions

Frequently Asked

Which product should I choose?

If your primary concern is that data never leaves a specific machine or network boundary, choose Edge. If you need a full enterprise platform with dashboards, billing, SSO, and compliance automation, choose Cloud. Many organizations run both — Edge on employee devices, Cloud as the enterprise backbone.

Do I need my own GPU?

For Edge: Ollama runs 7B models comfortably on any modern laptop (M-series Macs, recent PCs). No GPU required for the base experience. Cloud performs better with a GPU but runs fine on CPU for smaller models.

How does escalation work without leaking data?

Every escalation passes through a PII scan (email, phone, SSN, IBAN, credit card, IP, 11 entity types) that redacts sensitive data before sending. The user must grant explicit GDPR consent for escalation to happen at all. Every escalation is logged with a SHA-256 task hash for audit compliance.

Is this really open source?

Magi Edge is MIT-licensed — fully open, you can fork it, self-host it, inspect every line. Magi Cloud is BUSL-1.1 — the source is available for review and non-commercial use, with commercial licenses available. Both are developed in the open on GitHub.

Can I deploy this in my VPC / on-prem?

Yes, that's the whole point. Both products ship with Docker Compose for air-gapped deployments. Edge also works as a native Python install. No cloud services required at any layer.

Where is Magi Elior hosted?

The public demo runs on Hetzner in Nürnberg (Germany, EU). But that's just one deployment — the whole point of Magi is that you run it where your data already lives. We don't want your data.

Get Started

Install in under a minute.

No SaaS signup. No credit card. Run locally, in your VPC, or on-prem — your call.

Magi Edge (local, privacy-first)
pip install magi-elior ollama pull llama3.2 magi-elior start --mode root # root = standalone; for mesh see docs
Magi Cloud (full enterprise)
# Cloud is coming soon Join the waitlist → # On-prem Docker deploy at launch

Your data. Your rules.

Try either product right now. No signup. No cloud dependency.