# Central AI Hub — AI Document Index

> **Target**: AI Agents
> **Writing Style**: ASD-STE100 Simplified Technical English (`ste-writing`).

## Document Catalog (Inject Specific Document)

Read this index to inject the exact file you need. Do not search all files.

| Document Title | Path | Scope / Description |
| :--- | :--- | :--- |
| **System Overview** | `docs/outline/01-system-overview.md` | Explains the Hub purpose, its five steps, and the destinations. |
| **Configuration & Env** | `docs/outline/02-config-and-env.md` | Lists services, ports, env vars, and secret paths. |
| **Code Structure Map** | `docs/outline/03-code-map.md` | Shows the planned folder layout and entry points. |
| **AI Agent Runbook** | `docs/outline/04-agent-runbook.md` | Gives steps to build, test, and restart Hub work. |
| **Ask Contract** | `docs/ask-contract.md` | The interface between the Hub and every data project. |
| **Hub Inbound API** | `docs/hub-api.md` | The frozen v1 API from every way in to the Hub. |
| **Design Brief** | `hub_brief.md` | The agreed design. This file is the source of truth. |
| **Project Rules** | `AGENTS.md` | Mission, rules, build order, and project relations. |

---

## System Summary

The Hub is one service. Every way in reaches every ability through it. The Hub
does five steps: hear, understand, check, route, and answer. The Hub does not
hold a personality or a memory. The Hub does not do the destination work.

## Core Configuration

- **Env File**: `~/.config/environment.d/10-secrets.conf`
- **Config Directory**: `docs/`
- **Active Ports**: Hub 8788 (`HUB_PORT`, allocated 2026-10-10).

## Agent Restart Steps

1. Read the Document Catalog above. Inject only required files.
2. Read `hub_brief.md`.
3. Check git status: `git status`.
4. Check recent commits: `git log -n 5 --oneline`.
