# @kollguard/openai-agents

> Gate OpenAI Agents SDK (JS) tool calls through KollGuard Agent Watch: a tool input guardrail that allows, denies, or refuses a call, plus an approval pause for named human approvers. Sends tool and argument names only, never values.

Latest version **0.1.1** (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/openai-agents
pnpm add @kollguard/openai-agents
yarn add @kollguard/openai-agents
bun add @kollguard/openai-agents
```

## Facts

| | |
|---|---|
| Version | 0.1.1 |
| Published | 2026-11-19 |
| First published | 2026-11-19 |
| Weekly downloads | 0 |
| License | MIT |
| TypeScript types | bundled |
| Module format | ESM + CommonJS |
| Node | >=22 |
| Dependencies | 1 |
| Unpacked size | 18.1 KB |
| Author | Kollitech |
| Maintainers | kollguard |
| Keywords | openai, openai-agents, kollguard, agent-governance, ai-agents, guardrails, tool-approval, human-in-the-loop |

## Links

- npm: https://www.npmjs.com/package/@kollguard/openai-agents
- Homepage: https://kollguard.com/docs
- npm.io page: https://npm.io/package/@kollguard/openai-agents

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