# QVeris

> Every capability. One call away. QVeris is the capability routing network for agents — discover, compare, call, and settle real-world, verified capabilities through one protocol.

## What QVeris does
- Lets Agents discover the right capability with natural language instead of blindly picking APIs
- Provides quality signals (success rate, latency, price) so Agents can make informed choices
- Handles permissions, sandbox execution, billing, audit, and supply-side distribution
- Allows Agents to both consume and (in the future) provide capabilities

## Core protocol
- Discover: find capabilities with natural language (free)
- Inspect: view capability details, parameters, success rate, latency
- Call: invoke any capability, get structured results (1-100 credits per call)
- Covers finance, search, weather, maps, docs, social, blockchain, healthcare, and 15+ categories
- 99.99% call availability, <500ms average latency

## Use cases
- Agent needs to call third-party APIs or data sources
- Agent needs to dynamically discover and select capabilities
- Need a unified calling protocol with structured returns

## How QVeris relates to OpenClaw
- OpenClaw lets Agents use tools (runtime)
- QVeris lets Agents know which to call, why to trust it, and how to pay (capability routing)
- They are runtime + capability routing network, complementary not competing

## Access methods (recommended order)
- CLI v0.4.0 (recommended for agents): npm install -g @qverisai/cli — 80%+ fewer prompt tokens vs MCP, deterministic output, 10,000+ verified tools without prompt bloat
- MCP Server v0.5.0: npx @qverisai/mcp — for IDE integrations (Cursor, Claude Desktop, OpenCode)
- Python SDK: pip install qveris
- REST API (Global): https://qveris.ai/api/v1
- REST API (China): https://qveris.cn/api/v1
- Region auto-detected from API key prefix: sk-cn-xxx → China, sk-xxx → Global

## QVeris CLI — token-efficient agent tool use
- Agents call tools via subprocess (qveris discover/inspect/call), not prompt injection
- Up to 80% fewer tokens per tool invocation vs MCP — CLI runs outside the LLM context
- Zero external dependencies — only Node.js built-ins, instant install via npx
- Deterministic output schema: same command, same format, every time
- 10,000+ verified tools accessible without adding any schema to the prompt
- `qveris login` — interactive region selection + browser-based key retrieval
- `qveris doctor` — self-check diagnostics (Node.js, API key, region, connectivity)
- `qveris interactive` — REPL mode for discover/inspect/call loop
- `--json` flag for structured agent output, `--dry-run` to validate without credits
- `--codegen curl|js|python` to generate code snippets from successful calls
- Session index shortcuts: `qveris inspect 1`, `qveris call 2` (references last discover results)
- Shell completions: `qveris completions bash|zsh|fish`
- Install: curl -fsSL https://qveris.ai/cli/install | bash
- Docs: https://github.com/QVerisAI/QVerisAI/blob/main/packages/cli/README.md

## MCP Server tools
- `discover` — find capabilities by natural language query (free)
- `inspect` — view capability details, parameters, stats (free)
- `call` — execute a capability with parameters (1-100 credits)
- Deprecated aliases still supported: search_tools → discover, get_tools_by_ids → inspect, execute_tool → call
- Auto-generates session ID (UUID v4) per server instance
- Region auto-detected from API key prefix; override with QVERIS_REGION or QVERIS_BASE_URL

## Pricing
- Pay-as-you-go, not subscription
- Discover is free, Call is priced by value (1-100 credits)
- Free tier: 1,000 credits on signup
- $19 = 10,000 credits (never expire)

## Install
- OpenClaw users: https://qveris.ai/skill/instruct.md (official skill: skills/openclaw/qveris-official/SKILL.md)
- Cursor/Claude Code/OpenCode users: https://github.com/QVerisAI/QVerisAI/blob/main/agent/SETUP.md (uses skill: skills/qveris/SKILL.md)

## API docs
- CLI docs: https://github.com/QVerisAI/QVerisAI/blob/main/packages/cli/README.md
- MCP Server: https://github.com/QVerisAI/QVerisAI/blob/main/docs/en-US/mcp-server.md
- REST API: https://github.com/QVerisAI/QVerisAI/blob/main/docs/en-US/rest-api.md
- Online docs: https://qveris.ai/docs

## Open Ecosystem
- QVeris core engine is a managed service; all client-side tooling (MCP, SDK, skills, plugins) is open source
- GitHub org: https://github.com/orgs/QVerisAI/repositories
- ClawHub skills: https://clawhub.ai/skills?sort=downloads&q=qveris
- npm org: https://www.npmjs.com/org/qverisai
- Upstream contributions: openclaw/openclaw, openclaw/clawhub

## Links
- Website: https://qveris.ai (Global) / https://qveris.cn (China)
- Playground: https://qveris.ai/playground (Global) / https://qveris.cn/playground (China)
- Pricing: https://qveris.ai/pricing (Global) / https://qveris.cn/pricing (China)
- Get API Key: https://qveris.ai/account?page=api-keys (Global) / https://qveris.cn/account?page=api-keys (China)
- GitHub: https://github.com/QVerisAI/QVerisAI