Nirmos

Nirmos Documentation

Build, operate, and scale AI applications with the Nirmos platform.

Nirmos provides one infrastructure layer for model access, routing, caching, agents, workflows, observability, vector retrieval, and authentication.

Build with the TypeScript SDK

Use the official SDK for normalized Gateway requests, streaming, embeddings, images, and managed prompts.

Start with the AI Gateway

Connect an application through one OpenAI-compatible endpoint, then add provider and routing policy without changing the application contract.

Platform areas

AreaPurpose
AI GatewayOne request interface across providers
RoutingSelect models by policy, health, latency, and cost
CachingReuse exact or semantically equivalent responses
ObservabilityTrace attempts, tokens, latency, failures, and spend
Agents and workflowsRun durable tool and model execution paths

On this page