qverisai

# QVeris Tool Search & Execution

QVeris provides dynamic tool discovery and execution - search for tools by capability, then execute them with parameters.

## Setup

Requires environment variable:
- `QVERIS_API_KEY` - Get from https://qveris.ai

No additional dependencies — uses Node.js built-in `fetch`.

## Security

- **Credential**: Only `QVERIS_API_KEY` is accessed. No other env vars or secrets are read.
- **Network**: API key is sent only to `https://qveris.ai/api/v1` over HTTPS. No other endpoints are contacted.
- **Storage**: The key is never logged, cached, or written to disk.
- **Recommendation**: Use a scoped, revocable API key. Monitor usage at https://qveris.ai.

## Quick Start

### Search for tools
```bash
node scripts/qveris_tool.mjs search "weather forecast API"
```

### Execute a tool
```bash
node scripts/qveris_tool.mjs execute openweathermap_current_weather --search-id <id> --params '{"city": "London", "units": "metric"}'
```

## Script Usage

```
node scripts/qveris_tool.mjs <command> [options]

Commands:
  search <query>     Search for tools matching a capability description
  execute <tool_id>  Execute a specific tool with parameters

Options:
  --limit N          Max results for search (default: 10)
  --search-id ID     Search ID from previous search (required for execute)
  --params JSON      Tool parameters as JSON string
  --max-size N       Max response size in bytes (default: 20480)
  --timeout N        Request timeout in seconds (default: 30 for search, 60 for execute)
  --json             Output raw JSON instead of formatted display
```

## Workflow

1. **Search**: Describe the capability needed (not specific parameters)
   - Good: "weather forecast API"
   - Bad: "get weather for London"

2. **Select**: Review tools by `success_rate` and `avg_execution_time`

3. **Execute**: Call tool with `tool_id`, `search_id`, and `parameters`

## Example Session

```bash
# Find weather tools
node scripts/qveris_tool.mjs search "current weather data...

# QVeris Skill for OpenClaw

[中文文档](README.zh-CN.md) | English

A skill that enables OpenClaw to dynamically search and execute tools via the QVeris API.

## Features

- **Tool Discovery**: Search for APIs by describing what you need
- **Tool Execution**: Execute any discovered tool with parameters
- **Wide Coverage**: Access weather, stocks, search, currency, and thousands more APIs
- **Zero Extra Dependencies**: Uses only Node.js built-in `fetch` — no Python, no `uv`, no npm install

## Installation

### Prerequisites

- **Node.js 18+** (already present if you have OpenClaw installed)
- **QVERIS_API_KEY** — get your API key at https://qveris.ai

Set your API key:
```bash
export QVERIS_API_KEY="your-api-key-here"
```

### Install the Skill

**Option 1: Install via ClawdHub (Recommended)**
```bash
clawdhub install qveris
```

**Option 2: Install via NPX (For other coding agents)**
```bash
npx skills add hqman/qveris
```

**Option 3: Manual Installation**

Copy this folder to your OpenClaw skills directory:
```bash
cp -r qveris ~/.openclaw/skills/
```

## Usage

Once installed, OpenClaw will automatically use this skill when you ask questions about:
- Weather data
- Stock prices and market analysis
- Web searches
- Currency exchange rates
- And more...

### Manual Commands

```bash
# Search for tools
node scripts/qveris_tool.mjs search "stock price data"

# Execute a tool
node scripts/qveris_tool.mjs execute <tool_id> --search-id <id> --params '{"symbol": "AAPL"}'
```

## Author

[@hqmank](https://x.com/hqmank)

## License

MIT