your data.
qwen2.5:1.5b on Hetzner EU. No signup. 5 sec.
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.
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.
Magi Edge
- 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
Magi Cloud
- 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
Built for industries where data matters.
These are the scenarios where cloud AI is off the table — and where Magi Elior thrives.
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.
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.
Client privilege, protected by architecture.
Law firms reviewing contracts with client names. M&A teams summarizing deal documents. Litigation support with case strategy.
Sovereign AI for governments.
Ministries processing citizen data. Defense organizations analyzing intelligence. Regulators reviewing filings. All with strict data-residency requirements.
The Fractal Mesh
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.
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.
Edge vs Cloud
| Dimension | Magi Edge | Magi Cloud |
|---|---|---|
| Architecture | Fractal mesh (N nodes) | Monolith (single deploy) |
| Install | pip install + Ollama | Docker Compose stack |
| Inference | Ollama-first (local) | vLLM / LM Studio / HuggingFace |
| Privacy model | PII-gate on every hop | On-prem deployment |
| Auth | JWT + bcrypt + mTLS | SSO + SAML + SCIM + MFA |
| Compliance | GDPR (consent gate) | SOC 2, HIPAA, EU AI Act |
| Agents | ReAct engine + tools | 9 specialist agents |
| Billing | — | Stripe, 4 tiers, OEM |
| Frontend | Minimal chat UI | 74-page React dashboard |
| Plugin system | Local plugins (MIT) | Marketplace with 29 signed plugins |
| License | MIT | BUSL-1.1 |
| Best for | Data sovereignty, edge deployment | Enterprise AI at scale |
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.
Install in under a minute.
No SaaS signup. No credit card. Run locally, in your VPC, or on-prem — your call.
pip install magi-elior
ollama pull llama3.2
magi-elior start --mode root
# root = standalone; for mesh see docs
# 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.