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.

Quickstart

This guide walks through the core Hill90 workflow: creating an agent, configuring model access, and querying agent knowledge and usage.

Prerequisites

A modern web browser
An account on the Hill90 platform (contact the administrator)
For API access: a tool like curl, Postman, or any HTTP client

Accessing the Platform

The Hill90 UI is available at hill90.com. Signing in is not currently possible — see the note at the top of this page.

1. Health Check

Verify the API is running (no authentication required):

curl https://api.hill90.com/health

{
  "status": "healthy",
  "service": "api"
}

2. Authenticate

For all remaining calls, include your Keycloak JWT bearer token:

export TOKEN="YOUR_JWT_TOKEN"

See Authentication for details on obtaining tokens.

3. Create an Agent

Define an agent with a unique slug, name, and optional identity documents:

curl -X POST https://api.hill90.com/agents \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "my-first-agent",
    "name": "My First Agent",
    "description": "A test agent",
    "soul_md": "You are a helpful research assistant.",
    "rules_md": "Always cite your sources."
  }'

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "agent_id": "my-first-agent",
  "name": "My First Agent",
  "status": "stopped",
  ...
}

4. Create a Provider Connection

curl -X POST https://api.hill90.com/provider-connections \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "My OpenAI Key",
    "provider": "openai",
    "api_key": "sk-..."
  }'

{
  "id": "660e8400-e29b-41d4-a716-446655440001",
  "name": "My OpenAI Key",
  "provider": "openai",
  "is_valid": null,
  ...
}

5. Create a User Model

Define a model that references your provider connection:

curl -X POST https://api.hill90.com/user-models \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-gpt4o",
    "connection_id": "660e8400-e29b-41d4-a716-446655440001",
    "litellm_model": "openai/gpt-4o"
  }'

6. Assign Models to Your Agent

Update the agent with direct model assignment:

curl -X PUT https://api.hill90.com/agents/550e8400-e29b-41d4-a716-446655440000 \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model_names": ["my-gpt4o"]
  }'

7. Start the Agent

Start the agent container (requires admin role):

curl -X POST https://api.hill90.com/agents/550e8400-e29b-41d4-a716-446655440000/start \
  -H "Authorization: Bearer $TOKEN"

{
  "status": "running",
  "container_id": "abc123..."
}

The agent is now running in a sandboxed container with access to LLM inference (via assigned models) and persistent knowledge storage.

8. Browse Agent Knowledge

After the agent runs, browse what it has learned:

# List agents with knowledge entries
curl -H "Authorization: Bearer $TOKEN" \
  https://api.hill90.com/knowledge/agents

# List entries for a specific agent
curl -H "Authorization: Bearer $TOKEN" \
  "https://api.hill90.com/knowledge/entries?agent_id=my-first-agent"

# Search across knowledge
curl -H "Authorization: Bearer $TOKEN" \
  "https://api.hill90.com/knowledge/search?q=research+findings"

9. Query Usage

Check how much the agent has consumed:

# Summary of today's usage
curl -H "Authorization: Bearer $TOKEN" \
  https://api.hill90.com/usage

# Usage grouped by model
curl -H "Authorization: Bearer $TOKEN" \
  "https://api.hill90.com/usage?group_by=model"

{
  "total_requests": 42,
  "successful_requests": 40,
  "total_input_tokens": 15000,
  "total_output_tokens": 8000,
  "total_tokens": 23000,
  "total_cost_usd": 0.035
}

Next Steps

Authentication — Learn how to obtain and use JWT tokens
API Reference — Explore all available endpoints
Knowledge API — Browse agent knowledge entries
Architecture — Understand the platform architecture

Getting Started

Features

Architecture

API Reference

Endpoints

Quickstart

Quickstart

Prerequisites

Accessing the Platform

1. Health Check

2. Authenticate

3. Create an Agent

4. Create a Provider Connection

5. Create a User Model

6. Assign Models to Your Agent

7. Start the Agent

8. Browse Agent Knowledge

9. Query Usage

Next Steps

​Quickstart

​Prerequisites

​Accessing the Platform

​1. Health Check

​2. Authenticate

​3. Create an Agent

​4. Create a Provider Connection

​5. Create a User Model

​6. Assign Models to Your Agent

​7. Start the Agent

​8. Browse Agent Knowledge

​9. Query Usage

​Next Steps

Quickstart

Prerequisites

Accessing the Platform

1. Health Check

2. Authenticate

3. Create an Agent

4. Create a Provider Connection

5. Create a User Model

6. Assign Models to Your Agent

7. Start the Agent

8. Browse Agent Knowledge

9. Query Usage

Next Steps