Skip to main content
Deployed as a tenant of the Hill90 homelab — hill90.com serves the UI, and identity comes from the homelab’s Keycloak at auth.hill90.com, realm platform. Verified 2026-08-06 07:45 UTC: 23 containers running, 0 unhealthy — the homelab’s 16 and the application’s 7.Identity and data are the platform’s. The tenant’s databases sit on the homelab’s Postgres under a dedicated non-superuser role, and app-auth.hill90.com is not a live surface — it returns 404. Authorization uses client roles on the hill90-ui client rather than realm roles, so holding a homelab realm role does not by itself grant access to the application. A local stack runs its own Postgres, and --standalone its own Keycloak, so pages describing those locally remain accurate.Signing in was completed on 2026-07-30, reported by the operator who performed it. That is not independently re-verified here: realm platform has event storage disabled, so there is no server-side record left to read.Where a page in this section disagrees with AI Application, the overview is newer.

API Reference

The Hill90 API provides endpoints for agent management, chat, knowledge, model configuration, and platform operations.

Base URL

Authentication

Most endpoints require a valid JWT bearer token issued by Keycloak:
See Authentication for details on obtaining tokens. Health endpoints (/health, /health/detailed) are public.

Endpoint Groups

Agents

Create, configure, start, stop agents. Manage skills, webhooks, and runtime.

Chat

Create threads, send messages, stream responses, browser control.

Knowledge

Agent memory (AKM), shared knowledge library, hybrid search with pgvector.

Models & Policies

Provider connections, user models, model policies, usage tracking.

Agents

Agent lifecycle management — CRUD, start/stop, status, logs, skills, webhooks.

Chat

Real-time chat with agents — threads, messages, SSE streaming, browser control.

Models

Provider connections, user models, and model policies for BYOK inference.
Model names are resolved through a chain: requested model → alias resolution → BYOK provider model. See the OpenAPI spec for full schema details.

Auto-Generated Pages

The individual endpoint pages below are auto-generated from the OpenAPI specification with request/response schemas and example payloads.