Built-in stack: zero Chinese-origin. BYO at runtime: allowed.
A platform is what it can refuse to break. We architect for the bad day, not the demo day.
No Qwen / Aliyun / ByteDance / Baidu / Tencent / Huawei / ECharts / Ant Design / DingTalk / WeCom / Feishu in built-in deps. Customer plugs Custom provider at runtime — configuration-time choice, never the default. Running NEXUPIRA inside your own cloud is planned for Enterprise.
Sovereignty is not a feature flag — it is the construction. Encryption, isolation, audit, and origin policy are baked into the substrate before any feature ships on top.
- Per-account isolation
- AES-256-GCM at rest
- CSP nonce per request
- Rate limits + lockout
- 2FA + passkeys
- Admin audit log
Built-in excludes. BYO is the exception.
The built-in stack ships zero Chinese-origin technology — no bundled models, UI libs, observability, DB, deployment, npm or python deps. The single exception is customer BYO model at runtime via the Custom provider slot — configuration-time choice, never the default. UI surfaces it neutrally as Custom provider; no origin is celebrated or suppressed.
Absent from bundled deps, default LLM, and self-hosted observability.
- Qwen
- Aliyun
- ByteDance
- Baidu
- Tencent
- Huawei
- ECharts
- Ant Design
- DingTalk
- WeCom
- Feishu / Lark
Customer configures Custom provider in settings against any OpenAI-compatible endpoint.
Settings · LLMCustom in provider picker — no flag celebrationCustomers in regulated industries need a clean built-in supply chain. Their own runtime choices are their own.
No hidden inference proxies. Analytics and telemetry are limited to what our Privacy Policy lists.
Every decryption of a stored AI key or connection token is written to the audit log with the provider name.
Every control, every state, honestly labelled.
No security marketing. Each control is labelled Live or Planned.
Per-account isolation
LiveEach account has its own isolated database schema. Workspace data, chats, and workflows are isolated by construction.
AES-256-GCM at rest
LiveConnection tokens, AI provider keys, database connection strings and document content are encrypted with AES-256-GCM. Disconnecting a service deletes its tokens.
CSP nonce per request
LiveContent Security Policy nonce regenerated on every render. Inline-script attacks fail at the policy layer before they reach the page.
Rate limits + lockout
LiveRepeated failed sign-ins or 2FA codes lock the account for 15 minutes, and API calls are rate-limited per person. All traffic is served over HTTPS.
SAML 2.0 / OIDC SSO
PlannedSign-in through your company identity provider (Okta, Microsoft Entra ID, Google Workspace) is planned for Enterprise. Today: email and password with 2FA or passkeys.
Audit log
LiveDocument, bot and AI-provider changes, account deletion, and every decryption of a stored AI key or connection token are written to an audit log that admins can review.
2FA + Passkeys
LiveOptional TOTP two-factor with one-time backup codes, plus WebAuthn passkeys (Touch ID, Windows Hello, security keys). Per-account enrollment in Settings · Security.
Workspace controls AI scope. User controls identity.
Not all data sits at the same tier. Workspace-scoped is team-shared; User-scoped is personal. Memory Gatekeeper runs in user scope — your memories never leak to colleagues in the same workspace.
Workspace-scoped
- Documents
- Chat sessions
- Workflows
- Tool catalog
- Knowledge bots
User-scoped
- Memories (Gatekeeper)
- OAuth tokens
- LLM keys
- Personal preferences
Sovereignty, by construction.
Deploying in your own cloud, VPC or data center is planned for Enterprise and scoped project by project — talk to us. Your data, your decisions, your audit log.