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

# Overview

> Agent-ready spatial intelligence for construction video.

Vima turns egocentric construction footage into auditable spatial evidence.
Instead of asking a model to guess from raw video, Vima builds a compact evidence
layer first, then exposes it to humans and agents through a dashboard, HTTP API,
CLI, and MCP server.

<CardGroup cols={2}>
  <Card title="Evidence First" icon="scan-search">
    Frames are grounded with cached CII labels, zone attribution, and spatial
    context before they become an answer.
  </Card>

  <Card title="Agent Native" icon="bot">
    MCP and CLI interfaces let external agents inspect the same production
    evidence as the dashboard.
  </Card>

  <Card title="Small Production Footprint" icon="server">
    Expensive perception is precomputed offline, so the hosted services stay
    light enough for a 1 vCPU / 2 GB VPS.
  </Card>

  <Card title="Auditable Outputs" icon="clipboard-check">
    Tool responses are structured JSON with frame rows, zone metrics, and
    temporal evidence instead of ungrounded prose.
  </Card>
</CardGroup>

## Production Surfaces

| Surface    | URL                                   |
| ---------- | ------------------------------------- |
| Landing    | `https://vimaspatial.tech`            |
| API        | `https://vimaspatial.tech/api`        |
| MCP        | `https://vimaspatial.tech/mcp`        |
| MCP Health | `https://vimaspatial.tech/mcp/health` |

## Pipeline

```text theme={"dark"}
Hardhat footage
  -> sampled frames
  -> object boxes + optional Gemini Robotics-ER boxes
  -> merged boxes, masks, and depth
  -> CII labels and spatial zones
  -> object-event episodic memory
  -> cited dashboard / API / CLI / MCP response
```

## Current Hosted Facts

* `/api/cii/summary`: 30 masonry frames, 26 `P`, 0 `C`, 4 `NC`, 86.7% wrench time, and 11 raffle tickets.
* `/api/spatial/zones`: three 10-frame zones, currently reporting 90.0%, 100.0%, and 70.0% productive time.
* `/api/eval`: temporal evidence is served from cached or live JSON; the current hosted snapshot examines 8 frames, returns 5 accepted temporal claims, and shows a 0.600 to 0.792 spatial score lift from memory augmentation.
* Frontend evidence workspace: 118 temporal episodes are available for the demo review flow.
* `/mcp/health`: the hosted MCP service is deployed and healthy. The `/mcp` route itself is for streamable HTTP MCP clients, not plain browser GETs.
* `/api/demo`: present for local video-backed demos, but returns `video_unavailable` on production because the full source video is not bundled on the VPS.

<Note>
  Production serves cached evidence and small JSON tools. Heavy video,
  reconstruction, SAM, Depth Anything, and COLMAP work stays offline or in
  precomputed artifacts.
</Note>