Entry and control
nginx, Srasta API, Admin, license posture, model access, RBAC, rate limits, and signed service headers.
Architecture & Data Flow
Srasta is a single-perimeter governed AI platform. The runtime, memory, vector store, audit trail, tools, identity, and operator workflows run inside infrastructure the customer controls: their VPC, cluster, on-prem hosts, or single-node installation.
Trust Boundary
Users, tools, models, memory, storage, and audit are governed through a single customer-controlled runtime. Optional outbound paths are explicit, visible, and operator-configurable.
Inside the Perimeter
The main services run inside the customer environment. They are packaged as containers or Helm-managed workloads and share one operating story: identity-aware entry, governed execution, local storage, local audit, and operator-controlled egress.
nginx, Srasta API, Admin, license posture, model access, RBAC, rate limits, and signed service headers.
RAG API, Tool Gateway, LiteLLM routing, vLLM or Ollama local inference, and persona-scoped policy.
Postgres for state, Milvus for embeddings, MinIO for objects and backups, Valkey for cache and limits.
Zitadel identity, audit JSONL, hash-chain verification, optional SIEM forwarding, and operator runbooks.
Data Locations
Outbound Channels
Only used when operators configure external routes. Model access can be governed by role and persona.
Optional SIEM or S3 forwarding for audit events. Core audit still remains local when export is disabled.
Runtime license verification is offline against the embedded public key. Issuance and renewal are control-plane actions.
Install and feature-use metadata only. No prompts, responses, documents, audit content, or end-user identifiers.
Failure Behavior
Srasta separates runtime execution, identity, storage, audit export, and license issuance so a problem in one area does not silently compromise the whole platform.
External-routed requests fail clearly while local model routes can continue operating.
Local audit remains intact and forwarding can resume when the sink recovers.
Running deployments are unaffected because runtime verification is offline by design.
Admin health and operator surfaces show degraded state instead of pretending the runtime is healthy.
FAQ
Customer data lives inside the customer-controlled deployment: customer VPC, cluster, on-prem hosts, storage, vector database, and audit volumes. Srasta does not route customer prompts, documents, responses, audit records, or backups through Gandiva infrastructure in normal operation.
No. Srasta is designed as a customer-perimeter deployment. The runtime data plane runs inside the customer environment, while license issuance and optional operational telemetry are separate control-plane interactions.
Outbound traffic is operator-controlled: external model providers if configured, optional audit export sinks, license issuance or renewal, and optional operational telemetry that excludes prompt, response, document, audit-log, and end-user identifier content.
The main trust boundary is the customer infrastructure perimeter. External users enter through the Srasta API gateway, where TLS, identity, RBAC, model access, license posture, rate limits, and audit emission are enforced before requests reach internal services.
Security Review
The public page explains the data-flow model. The downloadable artifacts provide deeper evidence for security teams, auditors, and design partners.