What makes Kami Image Search notable?

1.1K downloads. Trust evidence available

How should Kami Image Search 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 Image Search

A skill by Kami SmartHome. Capture frames from your camera, describe them with AI, and search your visual history using natural language.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.0.7

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: 1.0.7release · observed Jun 10, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s170wja1qf8kmkzj5brvhsj1r185a522:kami-image-search

Install using `clawhub skill install s170wja1qf8kmkzj5brvhsj1r185a522:kami-image-search` 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-image-search before using production credentials.

Contract: missing

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

Documentation

CLAWHUB

123,003 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: kami-image-search
description: A skill by Kami SmartHome. Capture frames from your camera, describe them with AI, and search your visual history using natural language.
version: 1.0.0
author: kami-smarthome
tags:
  - smart-home
  - kami
  - smarthome
  - text-to-image search
  - image-search
  - visual-search
  - camera
  - rtsp
  - faiss
  - embedding
  - ai-vision
  - kamivision
  - monitoring
  - home-assistant
  - iot
  - edge-ai
triggers:
  - smart home
  - kami
  - text to image search
  - home assistant
  - image search
  - search image
  - find image
  - visual search
  - kami image
  - kami smart home
  - search camera
  - what did the camera see
  - find photo
  - search photos
  - look up image
  - camera history
  - check camera
metadata:
  openclaw:
    requires:
      bins:
        - python3.10
      hardware:
        cpu: "2+ cores (x86_64 / ARM64)"
        memory: "2 GB+"
        storage: "5 GB+"
        gpu: "optional"
      network:
        - "RTSP camera access (LAN)"
        - "Internet (KamiClaw API)"
      devices:
        - "RTSP IP camera"
    emoji: "🔍"
---

# Kami Image Search

> Search your camera's visual history with natural language.

Monitor your camera feed, capture frames automatically, and retrieve matching images by simply describing what you're looking for. Powered by the Kamivision cloud API for AI description and embedding generation.

### Features

- 🔍 Natural language image search
- 📸 Automatic frame capture from video streams
- 🧠 AI-powered image description (Kamivision API)
- 📁 Manual image import (JPEG / PNG / BMP / WebP)
- 🔁 Built-in duplicate frame detection
- ⏱ Time-range filtering
- 🏠 Designed for Kami SmartHome ecosystem

### Scenarios

- Doorstep delivery verification
- Home activity review
- Pet or child monitoring playback
- Batch photo indexing and retrieval

## Installation

```bash
bash setup.sh
```

Checks for Python 3.10, creates `.venv/`, and installs `opencv-python-headless`, `numpy`, `requests`, `Pillow`, `faiss-cpu`. Idempotent.

## Prerequisites

- Python 3.10 (setup.sh auto-detects system / pyenv / conda; auto-installs via conda or pyenv if missing)
- `image_config.json` configured with your stream URL(s) and Kamivision API key
- RTSP/RTMP camera(s) online and reachable (for capture mode)

## Kamivision API Key Setup

This skill requires a `KAMIVISION_API_KEY` to access the Kamivision cloud API.

**Check**: Read the `KAMIVISION_API_KEY` field in `image_config.json`.

- **If already configured (non-empty)** → Use it directly, no need to ask.
- **If empty** → Ask the user if they already have an API Key:
  - **Yes** → Enter the key directly. It will be saved to `image_config.json`.
  - **No** → Register at [Kamivision Flow](https://kamiclaw-skill.kamihome.com/) to obtain your API key. 🎁 **New users get 200 free credits on first registration.**

## Parameter Confirma

README.md

# Kami Image Search

Capture frames from video streams or import local images. Uses the Kamivision cloud API to generate image descriptions + text embeddings (2048-dim) in a single call, with FAISS vector indexing for natural language image retrieval.

## Architecture

```
Camera RTSP stream / Local image import
        │
        ▼
   Frame capture & dedup (pixel diff detection)
        │
        ▼
   Kamivision SUMMARY API (returns description + embedding)
        │
        ▼
   FAISS IndexFlatIP + SQLite storage
        │
        ▼
   Natural language query → Kamivision EMBED API → vector matching → ranked results
```

## Quick Start

### 1. Setup

```bash
bash setup.sh
```

Checks Python 3.10 (auto-installs via conda/pyenv if missing), creates Python virtual environment, installs dependencies.

### 2. Configure

Edit `image_config.json` (multi-camera example):

```json
{
  "cameras": [
    {
      "STREAM_URL": "rtsp://admin:[email protected]:554/stream1",
      "DEVICE_ID": "CAM-FRONT",
      "CAPTURE_INTERVAL": 10
    },
    {
      "STREAM_URL": "rtsp://admin:[email protected]:554/stream1",
      "DEVICE_ID": "CAM-BACK",
      "CAPTURE_INTERVAL": 15
    }
  ],
  "KAMIVISION_API_KEY": "your-api-key-here"
}
```

Each camera runs as an independent background process; `DEVICE_ID` must be unique. Legacy single-camera config (flat `STREAM_URL` / `DEVICE_ID` at top level, without the `cameras` array) is still supported.

> `KAMIVISION_API_KEY` is required. If you don't have one, register at [Kamivision Flow](https://kamiclaw-skill.kamihome.com/) to obtain it.

### 3. Usage

```bash
# Start background frame capture (all cameras)
python image_search.py --start-capture

# Start a specific camera
python image_search.py --start-capture --device CAM-FRONT

# Check capture status (all cameras or a specific one)
python image_search.py --status
python image_search.py --status --device CAM-FRONT

# Stop capture (all cameras or a specific one)
python image_search.py --stop-capture
python image_search.py --stop-capture --device CAM-FRONT

# Import local images
python image_search.py --import /path/to/photos/ --json

# Natural language search across all cameras
python image_search.py --search "person in blue jacket" --json

# Search a specific camera only
python image_search.py --search "keys on the table" --device CAM-FRONT --json

# Search with time range
python image_search.py --search "keys" --time-start 1777010000 --time-end 1777013000 --json

# List images from the last 24 hours
python image_search.py --list 24
```

## Configuration

| Field | Description | Default |
|-------|-------------|---------|
| `cameras` | Camera list (array). Each entry requires `STREAM_URL` and `DEVICE_ID` | — |
| `cameras[].STREAM_URL` | Per-camera video stream URL (RTSP/RTMP/HTTP) | `""` |
| `cameras[].DEVICE_ID` | Per-camera unique identifier | `CAM-001` |
| `cameras[].CAPTURE_INTERVAL` | Per-camera capture interval (overrides global, seconds) | `10` |
| `STREAM_UR

_meta.json

{
  "ownerId": "kn7e9156e1awf00v1sas2wkdfd85a4zh",
  "slug": "kami-image-search",
  "version": "1.0.7",
  "publishedAt": 1781073036368
}

skill-card.md

## Description:

A skill by Kami SmartHome. Capture frames from your camera, describe them with AI, and search your visual history using natural language.

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 capture or import camera images, index visual history, and retrieve matching images with natural-language queries. Developers can configure camera streams, retention, and search thresholds for RTSP-based monitoring workflows.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Camera frames, imported images, and search text may be sent to Kamivision for cloud inference.

Mitigation: Use the skill only when that data sharing is acceptable, verify KAMIVISION_API_URL is the intended HTTPS Kami endpoint, and avoid processing sensitive images unnecessarily.

Risk: Camera stream URLs and API keys can expose private credentials if stored or logged insecurely.

Mitigation: Restrict permissions on image_config.json and log files, avoid embedding camera passwords in stream URLs when possible, and rotate credentials if exposure is suspected.

Risk: The setup script can install Python tooling and may request sudo package installation for build dependencies.

Mitigation: Review setup.sh before running it and approve sudo installation only when system-wide changes are acceptable.

Risk: Captured images, imported images, SQLite metadata, and FAISS indexes are stored locally.

Mitigation: Set retention to the shortest practical period, protect the data directory, and delete local frame and index data when it is no longer needed.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/13681882136/skills/kami-image-search)
- [Publisher profile](https://clawhub.ai/user/13681882136)
- [Kamivision Flow](https://kamiclaw-skill.kamihome.com/)
- [Kamivision privacy policy](https://kamiclaw-skill.kamihome.com/privacy)
- [Kamivision API endpoint](https://kamiclaw-skill-api.kamihome.com/v1/detect)

## Skill Output:

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

**Output Format:** [Markdown guidance with inline shell commands and JSON CLI output]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May produce JSON search results, camera status output, configuration updates, and local image/index files.]

## Skill Version(s):

1.0.7 (source: server release evidence)

## 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.

image_config.json

{
  "cameras": [
    {
      "STREAM_URL": "rtsp://admin:[email protected]/stream1",
      "DEVICE_ID": "camera1"
    },
    {
      "STREAM_URL": "rtsp://admin:[email protected]/stream1",
      "DEVICE_ID": "camera2"
    }
  ],
  "OUTPUT_WIDTH": 640,
  "OUTPUT_HEIGHT": 360,
  "ENABLE_DESCRIPTION": true,
  "VLM_PROMPT": "",
  "EMBEDDING_MODE": "text",
  "KAMIVISION_API_URL": "https://kamiclaw-skill-api.kamihome.com/v1/detect",
  "KAMIVISION_API_KEY": "",
  "SIMILARITY_THRESHOLD": 0.35,
  "SEARCH_TOP_K": 5,
  "DATA_DIR": "./image_data",
  "RETENTION_DAYS": 30,
  "RECONNECT_DELAY": 3,
  "SKIP_DUPLICATE": true,
  "DUPLICATE_THRESHOLD": 5.0,
  "TIME_ZONE_OFFSET": -12,
  "CAPTURE_INTERVAL": 10
}

Github ReposUpdated 2d 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.