Pricing Plans
Simple pricing for
a private second mind.
Start free on your own machine. Go on-prem when your whole team needs the super memory graph — with zero data egress.
Starter
For trying Oryne on your own machine.
- On-device inference
- 1 connected app
- Smart inbox
- 30-day memory graph
- Community support
Pro
For professionals who live in their inbox.
- Everything in Starter
- Unlimited connected apps
- Unlimited memory graph
- One-click follow-ups & drafts
- Commitment tracking
- Bring-your-own model endpoints
- Priority support
Enterprise On-Prem
For teams with serious privacy requirements.
- Everything in Pro
- Full on-prem / air-gapped deployment
- Zero data egress, firewall-verifiable
- Run Llama, Mistral, Qwen or custom fine-tunes
- SSO / SAML, SCIM & audit logs
- Custom retention & compliance
- Dedicated support & SLA
Questions, answered.
Where does my data go?
Nowhere. In on-prem deployments, ingestion, embeddings, the memory graph and all LLM inference run entirely on infrastructure you control — verifiable with your own firewall logs.
Which models can I run?
Any open-weights model — Llama, Mistral, Qwen and more — or your own fine-tunes. Swap models with a single config flag, no redeploy needed.
Is there a free trial?
Yes. Pro comes with a 14-day free trial — no credit card required. Starter is free forever, and Enterprise pilots run on your own cluster.
Can Oryne run air-gapped?
Yes. Enterprise On-Prem ships as containers or a single binary with no external dependencies — deploy it where no packet ever leaves.