Skip to main content

TrustGate is one Go binary that boots one of three planes — Admin, Proxy, or MCP. In production each pod runs the same image with a different argument so the planes scale independently.

Install a data plane

SaaS hosts the planes. Private (Hybrid) runs them in your environment.

Request policies

Where rate limits, budgets, and guardrails attach on the path.

MCP plane

The :8082 server that aggregates MCP registries.

Metrics worker

The per-request event that leaves the request path over OpenTelemetry.
TrustGate ships a single binary (trustgate) that boots one HTTP server, chosen by its first argument. In production each pod runs the same image with a different argument, so the planes scale independently.

​
The three planes

Most teams configure TrustGate from the NeuralTrust console. The Admin plane is the control surface (console + REST); the Proxy and MCP planes are the data plane your traffic flows through.

​
Request lifecycle (proxy)

  1. A client calls the proxy with a consumer API key, a bearer JWT from the consumer’s IdP, or a client certificate.
  2. TrustGate resolves the gateway (from X-AG-Gateway-Slug or the host), the consumer (from the URL slug), and the applicable policies, then checks the caller against the consumer’s auth binding (allowed client ids or certificate subjects).
  3. The applicable policies run at their stages — rate limit, LLM budget, request size, guardrails, and other attached policies — sequentially or in parallel.
  4. The load balancer picks a healthy registry from the consumer’s pool (round-robin, weighted, least-connections, random, or smart routing), with fallback.
  5. The request is forwarded to the selected provider adapter (OpenAI, Anthropic, Bedrock, …), streaming when the client asked for it.
  6. The response returns and a telemetry event is exported with OpenTelemetry (background worker — off the request path).

​
Gateway discovery

GATEWAY_DISCOVERY_MODE controls how the proxy finds the gateway:
  • header (default, self-managed) — reads the X-AG-Gateway-Slug header, falling back to a Host match against {slug}.<GATEWAY_BASE_DOMAIN>.
  • subdomain (cloud) — Host-only.

​
Infrastructure

​
Caching & invalidation

To avoid a database round-trip per request, the proxy keeps an in-process TTL cache (CACHE_LOCAL_TTL, default 5m) of resolved gateways, consumers, and auths. Admin mutations publish invalidation events over Redis pub/sub, and the proxy flushes the affected entries — so config changes propagate without a restart.

​
Endpoints the proxy serves

All proxy traffic is shaped as /{consumer_slug}/..., and the inbound format is detected from the path: The inbound format is chosen by the path, independent of the upstream provider — TrustGate adapts between formats, so an OpenAI-format client can be routed to an Anthropic or Gemini upstream. Any other path returns 404. Streaming ("stream": true, or the Gemini :streamGenerateContent path) is supported on all routes; the proxy flushes each SSE chunk and surfaces mid-stream upstream failures as an explicit error event rather than a silent truncation.

​
Repository layout

TrustGate follows a hexagonal layout — domain entities and ports in pkg/domain, use-cases in pkg/app, and adapters in pkg/infra (providers, policies, load balancer, database, telemetry). Configuration is environment-only; see Deployment configuration.