# @kollguard/core

> Framework-neutral client for KollGuard Agent Watch: authorize an agent's tool calls (allow, deny, or wait for a named human), export evidence spans, and try it locally with no signup. Sends names and classes only, never argument values.

Latest version **0.2.0** (published 2026-11-19) · MIT license · 0 weekly downloads

_The full health report (score, vulnerabilities, README, dependency tree, version history) is being computed; this document will grow once it lands._

## Install

```sh
npm install @kollguard/core
pnpm add @kollguard/core
yarn add @kollguard/core
bun add @kollguard/core
```

## Facts

| | |
|---|---|
| Version | 0.2.0 |
| Published | 2026-11-19 |
| First published | 2026-11-19 |
| Weekly downloads | 0 |
| License | MIT |
| TypeScript types | bundled |
| Module format | ESM + CommonJS |
| Node | >=20 |
| Dependencies | 0 |
| Unpacked size | 203 KB |
| Author | Kollitech |
| Maintainers | kollguard |
| Keywords | kollguard, agent-governance, ai-agents, guardrails, human-in-the-loop, authorization, opentelemetry, security |

## Links

- npm: https://www.npmjs.com/package/@kollguard/core
- Homepage: https://kollguard.com/agent-authorization
- npm.io page: https://npm.io/package/@kollguard/core

---
_Source: https://npm.io/package/@kollguard/core · Machine-readable twin of the npm.io package page. Health data is recomputed on every publish._
