What makes Kami Fall Detection notable?

1.1K downloads. Trust evidence available

How should Kami Fall Detection be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Kami Fall Detection

Detect fall events from RTSP camera streams using KamiClaw cloud API. No local GPU needed.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.1.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.1.2release · observed Jun 10, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s170wja1qf8kmkzj5brvhsj1r185a522:kami-fall-detection

Install using `clawhub skill install s170wja1qf8kmkzj5brvhsj1r185a522:kami-fall-detection` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/13681882136/kami-fall-detection before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-13681882136-kami-fall-detection/snapshot"

Documentation

CLAWHUB

148,283 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: kami-fall-detection-cloud
description: Detect fall events from RTSP camera streams using KamiClaw cloud API. No local GPU needed.
version: 1.0.9
author: kami-smarthome
tags:
 - smart-home
 - fall-detection
 - elderly-care
 - cloud-ai
 - rtsp
 - camera
triggers:
 - detect fall
 - fall detection cloud
 - check for falls
 - monitor elderly
 - cloud fall detection
 - home assistant
 - smart home
metadata:
 openclaw:
  requires:
   bins:
   - python3
   - ffmpeg
   env:
   - KAMICLAW_API_KEY
  primaryEnv: KAMICLAW_API_KEY
  emoji: "🚨"
  hardware:
   cpu: "4+ cores (x86_64 / ARM64)"
   memory: "8 GB+"
   storage: "20 GB+"
   gpu: "optional (speed up ONNX inference)"
   network:
   - "RTSP camera access (LAN)"
   - "Internet (KamiClaw API)"
   devices:
   - "RTSP IP camera"
---

# Kami Fall Detection (Cloud)

Detect fall events from RTSP camera streams using the KamiClaw cloud API. No local GPU needed — all inference runs server-side.

---

## 🚀 Quick Start

1. **Get API key** → https://kamiclaw-skill.kamihome.com (200 free credits for new users)
2. **Tell the agent**: Your API key + RTSP camera URL
3. **Choose notifications**: Feishu / Telegram / Discord (any combination)
4. **Agent configures everything** automatically
5. **Run!** → Monitors 24/7, alerts instantly on fall detection

---

## What It Does

- 🎥 Monitors RTSP camera streams continuously
- 🧠 Uses cloud AI to detect fall events (active falling, fallen posture, etc.)
- 📱 Sends instant notifications via Feishu, Telegram, or Discord
- 💾 Saves alarm video clips for review (optional)
- 🔄 Auto-reconnects if stream drops

---

## 🔒 Privacy & Data Policy

**In short:** Only 8-second alarm clips are sent to the cloud for AI analysis. No continuous streaming, no audio, no full video.

| What | Local | Cloud |
|------|-------|-------|
| Video stream / file | ✅ Processed locally | ❌ Never sent |
| 8-second alarm clips | ✅ Saved (optional) | ✅ Sent for AI analysis |
| Audio | ❌ Not collected | ❌ Not collected |

> 📄 **Full details:** Read our [Privacy Policy](https://kamiclaw-skill.kamihome.com/privacy) for complete information on data handling, retention, and your rights.

### Quick Tips

- **Disable local storage:** Set `save_alarm_clips: false` to not save clips locally
- **Clean up old files:** `find logs/clips/ -type f -mtime +30 -delete`
- **Protect your API key:** Never commit `config.json` to git

> ℹ️ AI analysis requires sending alarm clips to the cloud API. Processed clips are retained per the provider's data retention policy.

---

## Configuration

All settings are in `config.json`. The agent auto-fills this when you provide values in chat.

### Essential Settings

| Field | Default | Description |
|-------|---------|-------------|
| `api_key` | `""` | **Required.** KamiClaw API key |
| `cameras` | `[]` | **Required.** Array of `{name, rtsp_url}` entries. Single entry: `name` optional, defaults to `"default"`. Two or more entries: every entry must have a unique non-empty

README.md

# Kami Fall Detection (Cloud)

Detect fall events from RTSP camera streams using the **KamiClaw cloud API**. No local GPU required — all heavy inference runs server-side. Designed for elderly-care monitoring with optional Feishu alarm notifications.

---

## Table of Contents

- [Features](#features)
- [How It Works](#how-it-works)
- [Project Structure](#project-structure)
- [Requirements](#requirements)
- [Installation](#installation)
- [Configuration](#configuration)
  - [KamiClaw API Key](#kamiclaw-api-key)
  - [Cameras](#cameras)
  - [Feishu Notifications (Webhook)](#feishu-notifications-webhook)
  - [Full Config Reference](#full-config-reference)
- [Usage](#usage)
- [Output Format](#output-format)
- [Logs](#logs)
- [Exit Codes](#exit-codes)
- [Troubleshooting](#troubleshooting)

---

## Features

- 🚨 **Real-time fall detection** from RTSP camera streams
- ☁️ **Cloud-based inference** — no local GPU or heavy ML libraries needed
- 🔁 **Auto-reconnect** when the RTSP stream drops
- 🎬 **Automatic alarm clip saving** (MP4) on fall events
- 📩 **Feishu webhook notifications** for instant alerts
- 📝 **Structured logs** (JSON Lines) for alarms and transitions
- ⚙️ **Flexible configuration** via `config.json`, CLI args, or environment variables

---

## How It Works

A two-stage pipeline keeps cloud usage low while maintaining high detection quality:

1. **Stage 1 — Local change detection (CPU only)**
   Lightweight frame-differencing on 128×128 grayscale frames. A rolling pre-buffer (default 4s) is maintained. When a significant temporal change is detected, Stage 2 is triggered.

2. **Stage 2 — KamiClaw cloud analysis**
   The skill collects post-transition frames (default 4s), resizes the clip to a 640×360 letterboxed canvas, writes it to a temp MP4, and sends it to the KamiClaw API (`detectType: FALL`, `detectSubType: SK_FALL_DETECTION`). If a fall is detected, a JSON alarm line is emitted and the clip is optionally saved.

3. **Auto-reconnect**
   If the RTSP stream disconnects, the skill retries every 5 seconds and seamlessly resumes monitoring.

---

## Project Structure

```
kami-fall-detection-cloud/
├── SKILL.md                      # Skill metadata & agent instructions
├── README.md                     # This file
├── config.json                   # Runtime config (api_key, rtsp_url, etc.)
├── fall_detect_cloud_skill.py    # Main entry point
├── feishu_notifier.py            # Feishu webhook/API notification module
├── setup.sh                      # Virtualenv + dependencies installer
└── requirements.txt              # Python dependencies
```

Generated at runtime:

```
logs/
├── app.log                       # Rotating daily application log
├── alarms.jsonl                  # Alarm & clip-analysis events (JSON Lines)
├── transitions.jsonl             # Stage-1 transition events (JSON Lines)
└── clips/                        # Saved alarm MP4 clips
```

---

_meta.json

{
  "ownerId": "kn7e9156e1awf00v1sas2wkdfd85a4zh",
  "slug": "kami-fall-detection",
  "version": "1.1.2",
  "publishedAt": 1781073098896
}

skill-card.md

## Description:

Detects fall events from RTSP camera streams using the KamiClaw cloud API without requiring a local GPU.

This skill is ready for commercial/non-commercial use.

## Publisher:

[13681882136](https://clawhub.ai/user/13681882136)

### License/Terms of Use:

MIT-0

## Use Case:

External users and smart-home operators use this skill to configure and run RTSP camera fall monitoring, receive fall alerts, and review saved alarm clips.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: RTSP URLs and camera credentials may expose private camera access if placed directly in config files or logs.

Mitigation: Use camera-owner consent, prefer secret handling that avoids credentials in RTSP URLs when possible, and keep config.json and logs private.

Risk: Alarm clips are sent to the KamiClaw cloud API for fall analysis and may be retained according to the provider policy.

Mitigation: Tell operators that alarm clips leave the local environment, review the provider privacy policy, and disable saved clips when local retention is not needed.

Risk: Configured Feishu, Telegram, or Discord notifications can send fall-event details and optional media to third-party services.

Mitigation: Enable only required channels, restrict webhook and bot access, and confirm recipients before monitoring live cameras.

Risk: The Feishu webhook fallback can upload an image to sm.ms when Feishu app credentials are not configured.

Mitigation: Configure Feishu OpenAPI image upload credentials when inline images are needed, or disable posture image sharing for sensitive deployments.

Risk: The installer may recreate an existing conda environment named kami-fall.

Mitigation: Review the local environment before running setup.sh and preserve any existing kami-fall environment that should not be replaced.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/13681882136/skills/kami-fall-detection)
- [KamiClaw API Registration](https://kamiclaw-skill.kamihome.com)
- [KamiClaw Privacy Policy](https://kamiclaw-skill.kamihome.com/privacy)

## Skill Output:

**Output Type(s):** [guidance, configuration, shell commands, json, markdown]

**Output Format:** [Markdown guidance with configuration edits, shell commands, JSON alarm records, and notification setup details]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Runtime output may include stdout JSON, JSON Lines logs, optional MP4 alarm clips, and Feishu, Telegram, or Discord notifications.]

## Skill Version(s):

1.1.2 (source: server release metadata; artifact frontmatter reports 1.0.9)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

config.json

{
  "api_key": "",
  "cameras": [],
  "run_time": 0,
  "pre_seconds": 3.0,
  "post_seconds": 3.0,
  "save_alarm_clips": true,
  "feishu_webhook_url": "",
  "feishu_app_id": "",
  "feishu_app_secret": "",
  "telegram_bot_token": "",
  "telegram_chat_id": "",
  "discord_webhook_url": "",
  "discord_bot_token": "",
  "discord_channel_id": "",
  "fall_posture_image": "resources/fall_postures.png"
}

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.