---
title: "Agents"
description: "How AI agents use Klav: their own identity and permissions, your approvals, secrets they use without seeing, the log, and pausing them."
image: "https://docs.klav.dev/og.png"
---

> Documentation Index
> Fetch the complete documentation index at: https://docs.klav.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Agents

This section explains how an AI agent uses your Klav vault: with its own identity and only the permissions you grant, asking you when the policy says so, and using secrets without seeing them. If you are an agent reading this, [How agents work](https://docs.klav.dev/agents/how-agents-work/) says exactly what you can and cannot get.

1. [How agents work](https://docs.klav.dev/agents/how-agents-work/): identity, the six words, `allow`, `ask` and `deny`, and the permissions.
2. [Connect an agent](https://docs.klav.dev/agents/connect-an-agent/): `klav client connect`, `klav mcp` and the skill.
3. [Approvals and tasks](https://docs.klav.dev/agents/approvals-and-tasks/): when an agent waits for you, and one approval for a whole job.
4. [Use secrets without seeing them](https://docs.klav.dev/agents/use-secrets-without-seeing-them/): `klav agent run`, `inject` and `fill`, `klav.toml` and `klav run`.
5. [The activity log](https://docs.klav.dev/agents/activity-log/): what each agent did, and what it saw.
6. [Pause, change or revoke an agent](https://docs.klav.dev/agents/pause-and-revoke/): stop every agent at once, change an agent's permissions, or take its access away.

Source: https://docs.klav.dev/agents/index.mdx
