The Universal AI Gateway
for Azure.

Route fast text models and complex agents through a single Kimss key. Onboard in five minutes as a solo developer. Scale on the same gateway with multi-tenant billing, telemetry, and audit your CTO will sign off on.

Get your API key → Read the architecture Documentation
Kimss AI Agent Representation

Why Kimss?

One key from prototype to production. The same gateway your weekend hack uses is the control plane your enterprise audits.

⚡
Zero-Friction SDK
pip install kimss and you’re calling GPT, Llama, or Mistral in under five minutes. No Foundry setup, no APIM policies, no IAM rabbit hole — just one key, one client, and client.models.create(...).
↔
One Gateway. Two Playgrounds.
Lightning-fast text models (Grok, Llama, Mistral, GPT) and full agentic workflows (vector stores, code interpreter, function tools) ride the same Kimss key. Switch by changing one parameter — never by rewriting your stack.
📊
Enterprise Control, Already Wired
Every call is metered, attributed, and logged at the gateway. Azure Monitor delivers immutable, Article 12–aligned audit trails; Redis-enforced credit pools cap spend per tenant in real time; Managed Identity replaces long-lived keys to Foundry.
01 — ANALYTICS

Granular Usage Reporting

Gain deep visibility into your platform's performance. Monitor API calls, track agent activity over time, and generate comprehensive telemetry reports.

  • Real-time API call tracking and cost analysis
  • Customizable telemetry dashboards for resource allocation
  • Automated daily, weekly, or monthly usage exports
02 — ORCHESTRATION

Centralized Agent Control

View and manage your organization's AI agents, configurations, and models from a single dashboard for ultimate governance.

  • Instantly toggle execution environments and models
  • Manage file access and custom tool bindings securely
  • Version control for agent system prompts and logic
03 — CREDIT POOLS

Real-time billing with hard and soft limits

Assign token budgets per tenant, department, or project. Redis-enforced limits ensure costs never spiral, even under unexpected load.

  • Configurable soft alerts and hard caps enforced at the gateway layer
  • Live progress widgets visible to tenants for self-service awareness
  • Automatic monthly pool resets with carry-forward policy options
  • PostgreSQL audit trail for every credit deduction event
04 — KNOWLEDGE

Unified Data Assets

Centralize your organization's contextual knowledge base. Securely manage vector stores, threads, and files across all your agents.

  • Single, compliant source of truth for all AI operations
  • Secure isolation of tenant data and vector stores
  • Automated indexing and retrieval optimization
Usage Report Dashboard Agent Management Dashboard Credit Pool Dashboard Data Assets Dashboard

How Kimss Works

Click on a component to explore the data flow securely routing your requests.

💻
Client Layer
APP
➔
🛡️
Azure APIM
Gateway
➔
⚡
FastAPI Core
Python App
➔
🗄️
Data Layer
PG & Redis
➔
🧠
AI Foundry
Agents
System Overview
Select any stage in the pipeline above to see how Kimss processes, secures, and tracks your AI interactions.

Transparent Multi-Tenant Billing

Azure Monitor and Log Analytics provide immutable, regulation-ready audit trails at the API gateway. Credit pools enforce spend limits per tenant in real time via Redis.

Live Tenant Usage Tracking

Tenant ID: Acme_Corp
Current Token Usage 0 / 5,000,000
Soft Limit (80%)
PostgreSQL Logged
Redis Cache Enforced

Built for Regulated Industries

Kimss is architected on Azure-native compliance primitives you can cite in procurement questionnaires. This is our technical design posture — not legal advice; your counsel validates fit for your sector.

EU AI Act — Article 12

Automatic, immutable AI logs

API Management diagnostic settings feed Log Analytics for gateway-level records. Token metrics use azure-openai-emit-token-metric with per-tenant dimensions for cost and governance dashboards.

GDPR — Data residency

Regional AI processing

Tenant slug maps to the correct Azure AI Foundry region via APIM backends and Named Values — no client-supplied region header. Project paths stay under /api/projects/{tenant}/… for a consistent data model.

Zero-trust

Managed identity to models

Gateway backends authenticate to Foundry with Managed Identity — no long-lived API keys in APIM policies for model traffic. Optional SDK-side PII scrubbing before traffic reaches the gateway.

Request our compliance pack

Dynamic Tool Registry

Equip your agents with custom, secure functions. Kimss strictly enforces access control, ensuring agents only call registered backend tools.

🏷️
get_project_quote
Fetches dynamic pricing for clients
{
  "agent_id": "agt_19283",
  "action": "execute_tool",
  "parameters": { "scope": "enterprise" }
}
📦
get_order_status
Queries live DB for logistics tracking
{
  "agent_id": "agt_55421",
  "action": "execute_tool",
  "parameters": { "order_id": "ORD-882" }
}
📑
fetch_audit_logs
Admin tool for compliance reporting
{
  "role": "admin",
  "action": "telemetry_recent",
  "parameters": { "limit": "100" }
}