# Live video · VideoDB

> Build agents for live video.

Nobody can watch every feed. VideoDB reads cameras, drones and screens as the video arrives, raises the events you describe in plain language, and sends each alert with the clip behind it.

Canonical: https://videodb.io/live-video · Talk to us: https://videodb.io/contact.md · Live demo: https://demo.rts.videodb.io/intruder-detection

The page opens with a wall of six live camera feeds: a street junction from above, a yard at night, a subway platform, a pedestrian crossing, a building site seen from a drone and a city street at night. The yard camera is outlined in orange, with an alert, while a person walks across it.

## Watch for anything you can describe

Connect a feed and write the event as a sentence. VideoDB reads the video in short windows and sends an alert when one of them matches.

- **Sources**: RTSP cameras, NVRs and drone gateways, plus screens and microphones, from one feed to thousands.
- **Events**: a sentence, such as "a person is checking the lock". Edit it to watch for something else.
- **Models**: a vision-language model with your prompt, or your own detector as an analyzer.
- **Alerts**: over a webhook or a WebSocket, each with the reason it fired and a clip of the moment. The payload carries `label`, `confidence`, `explanation` and `stream_url`.
- **History**: with storage on, every feed stays searchable in plain language, and each result is a clip.

The notebook that runs this example: [Intrusion detection](https://colab.research.google.com/github/video-db/videodb-cookbook/blob/main/real_time_streaming/Intrusion_Detection.ipynb).

## Try it on a live stream

Two demos run on sample feeds: a camera on a property, and a dashcam on the road. Both run on VideoDB's public sample streams. On the page the demo plays in a window, behind a loader until its video is there.

- Intruder detection: https://demo.rts.videodb.io/intruder-detection
- Dashcam: https://demo.rts.videodb.io/dashcam-demo

## Start from an event that already runs

Each row is a notebook on a public sample stream. Change the sentence to watch for something else. The cookbook: https://github.com/video-db/videodb-cookbook/tree/main/real_time_streaming

| Setting | The event, as it is written | Notebook |
| --- | --- | --- |
| Property | "Detect if a person is interacting with the door or visibly checking the lock." | [Intrusion detection](https://colab.research.google.com/github/video-db/videodb-cookbook/blob/main/real_time_streaming/Intrusion_Detection.ipynb) |
| Roads | "Detect if an accident or vehicle collision takes place." | [Road monitoring](https://colab.research.google.com/github/video-db/videodb-cookbook/blob/main/real_time_streaming/Road_Monitoring.ipynb) |
| Floods | "Detect sudden flash floods or water surges." | [Flash flood detection](https://colab.research.google.com/github/video-db/videodb-cookbook/blob/main/real_time_streaming/Flash_Flood_Detection.ipynb) |
| Homes | "Detect if the baby is trying to escape or climbing out of the crib." | [Baby crib monitoring](https://colab.research.google.com/github/video-db/videodb-cookbook/blob/main/real_time_streaming/Baby_Crib_Monitoring.ipynb) |
| Public spaces | "Detect luggage left unattended for 1+ minute." | [Multi-camera surveillance](https://colab.research.google.com/github/video-db/videodb-cookbook/blob/main/real_time_streaming/multicam/Multicam_Public_Surveillance.ipynb) |
| Live sport | "Detect when a batsman hits a six." | [Cricket match monitoring](https://colab.research.google.com/github/video-db/videodb-cookbook/blob/main/real_time_streaming/Cricket_Match_Monitoring.ipynb) |

## Watch a feed in code, or in a sentence

One file connects a camera, describes the event and says where the alert goes. The stream is a public sample, so it runs as it is with a free API key. In Claude or ChatGPT the same jobs are plain requests: "What is the front door camera showing right now?", "Tell me when someone checks the lock.", "Show me every delivery from this week." How a feed becomes memory: https://videodb.io/agent-memory.md

```python
import videodb

conn = videodb.connect()
coll = conn.get_collection()

# 1. Connect the feed and keep its history
cam = coll.connect_rtstream(
    url="rtsp://samples.rts.videodb.io:8554/intruder",
    name="Front door", store=True)

# 2. Read it in 5-second windows and index what the model sees
seen = cam.understand(
    segmentation={"type": "time", "window": "5s"},
    analyzers=[{"type": "vlm", "name": "scene",
                "sampling": {"frame_count": 2},
                "config": {"prompt": "Describe the people and what they do."}}],
    store=True)
index = cam.index(name="front-door", source=seen.outputs["scene"],
                  use_for=["semantic"])

# 3. Describe the event, and say where the alert goes
event = conn.create_event(
    event_prompt="Detect if a person is checking the lock.",
    label="lock_checked")
index.create_alert(event_id=event,
                   callback_url="https://example.com/hooks/camera")

# Later: ask what happened, and play the answer
found = cam.search(query="a delivery left at the door", index_id=index.id)
found.get_shots()[0].play()
```

## From the first feed to a whole site

A four-week pilot on your own cameras, in our cloud or yours.

1. **Week 1, first feeds live**: ten cameras connected, the events agreed, and an engineer from our team working with yours.
2. **Week 2, models and dashboards**: your own model runs as an analyzer where you have one, and alerts reach the tools your operators already use.
3. **Weeks 3 and 4, the whole site**: a hundred feeds or more, with the alerts checked against incidents you already have on record.

## Build it into your own product

For companies that sell monitoring, and for the integrators and clouds that serve them.

- **Brand**: VideoDB runs inside your product, under your name.
- **Models**: detectors you have trained keep running, with the feeds, the index and the alerts around them.
- **Region**: deployed in your cloud, in the region your buyers need.

## Run in our cloud or yours

VideoDB is video infrastructure for agents and devices that see. 1,000+ developers and agents use it every week, and it has processed 300+ TB of video. Runs on AWS, Google Cloud and Azure, or your own cloud. SOC 2 Type II, GDPR and ISO 27001 compliant. Security: https://videodb.io/legal/security.md

## Run a pilot on your own cameras

Tell us what you need to catch and where the cameras are. We reply within one business day. [Talk to us](https://videodb.io/contact.md) · [Add to Claude](https://videodb.io/claude) · [Add to ChatGPT](https://videodb.io/chatgpt)

## Use VideoDB in your agent

VideoDB lets an AI agent watch, search and clip video.

- **Claude**: [Add VideoDB from the plugin directory](https://videodb.io/claude)
- **ChatGPT**: [Add VideoDB from the plugin directory](https://chatgpt.com/plugins/videodb)
- **Claude Code**: `claude mcp add --transport http videodb https://mcp.videodb.io/mcp`
- **Cursor or any MCP client**: Add the remote MCP server and log in once: `https://mcp.videodb.io/mcp`

Free to start: $20 of credits, no credit card. [Steps for every client](https://docs.videodb.io/pages/mcp/connect).
