> ## Documentation Index
> Fetch the complete documentation index at: https://docs.deepmyst.com/llms.txt
> Use this file to discover all available pages before exploring further.

# The OS Stack

> Built like infrastructure — six layers every agent and request inherits

DeepMyst is built like infrastructure. Six layers, where every request inherits
identity from the bottom and policy from above. The same stack that runs your
first agent runs every agent — there's no second system for production.

## The six layers

| Layer          | What it is                    | Includes                                                  |
| -------------- | ----------------------------- | --------------------------------------------------------- |
| **Shell**      | How humans use it             | Chat, copilot, embeds, public portals                     |
| **Agents**     | First-class processes         | Voice, canvas, document, workflow, kanban, form, and more |
| **Memory**     | What agents know              | Knowledge graph, documents, datasources, history          |
| **Skills**     | What agents can do            | Built-in tools, MCP, web search, sub-agents               |
| **Models**     | What powers their thinking    | 500+ models, OpenAI-compatible, auto-failover             |
| **Governance** | The rules everything inherits | SSO, RBAC, cascading policy, KYT, audit                   |

<CardGroup cols="2">
  <Card title="Shell" icon="terminal">
    The surfaces people touch. Embed an agent anywhere, share a link, or hand off
    to a chat surface.
  </Card>

  <Card title="Agents" icon="boxes-stacked">
    First-class processes in a dozen shapes — voice, canvas, document, workflow,
    kanban, form, and more.
  </Card>

  <Card title="Memory" icon="brain">
    The persistent layer every agent reads from: knowledge graph, documents,
    connected datasources, and history.
  </Card>

  <Card title="Skills" icon="wrench">
    The tools and integrations every agent can invoke — built-in tools, MCP, web
    search, and sub-agents.
  </Card>

  <Card title="Models" icon="microchip">
    One API across every leading model. Swap providers without rewriting code, with
    automatic failover.
  </Card>

  <Card title="Governance" icon="shield-halved">
    Identity, cascading policy, inline security, and audit — inherited by every
    request, logged forever.
  </Card>
</CardGroup>

## How a request flows

Every call — whether from an agent or a direct API request — runs the same
pipeline. DeepMyst handles identity, policy, security, optimization, and metering
around a pluggable gateway hop:

1. **Auth** — validate the API key
2. **Policy lookup** — resolve the key → app → dept → org cascade
3. **KYT inline classification** — injection, PII, toxicity, and intent in under 15ms
4. **Guardrail enforcement** — block, flag, or redact based on policy
5. **Credit & rate check** — enforce RPM/TPM limits and budgets
6. **Optimization** — losslessly compress context
7. **Gateway** — route, proxy, and return from the chosen model
8. **Metering** — record usage and calculate cost
9. **Enrichment** — async KYT Pass 2 and behavioral analytics
10. **Events** — emit webhooks, write the audit log, update analytics

The model provider never sees user identity, classification results, or
uncompressed requests — DeepMyst handles those before and after the gateway hop.

## One API, every model

The Models layer is an OpenAI-compatible gateway. Point your base URL at DeepMyst
and the same SDK works across 500+ models from every major provider. A/B test one
model against another with a single config flip — your code never changes.

```python theme={null}
from openai import OpenAI

client = OpenAI(
    api_key="your-deepmyst-api-key",
    base_url="https://api.deepmyst.com/v1",
)

# Swap the model string; everything else stays the same
client.chat.completions.create(
    model="claude-opus-4-5",   # or gpt-5, gemini-3-pro-preview, ...
    messages=[...],
)
```

## Pluggable gateway

The Models layer is designed to run behind multiple gateway adapters through a
single interface, so routing infrastructure can change without touching the layers
above it. The key principle: the gateway adapter never sees user identity,
classification results, or uncompressed requests — those are handled by DeepMyst
core, so optimization and governance stay consistent no matter what's underneath.

## Next steps

<CardGroup cols="2">
  <Card title="Agent Builder" icon="wand-magic-sparkles" href="/agents">
    Build on the Agents layer in human language
  </Card>

  <Card title="Governance" icon="shield-halved" href="/governance">
    Configure the rules every layer inherits
  </Card>
</CardGroup>