---
title: "agenthold"
description: "Self-hosted, multi-user platform for running many persistent AI agents, each in its own sandbox."
---

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

# agenthold

agenthold runs AI coding agents (Claude Code, Codex and others) on a server you control. Every agent gets its own Docker sandbox with a home directory that survives sleep and restarts, and people talk to it from a chat in the browser.

- **One sandbox per agent.** Agents sleep when idle and wake on demand. Files, history and sessions stay on disk.
- **Secrets stay outside.** An egress proxy injects credentials into outgoing requests, so agents use API keys and logins they never see. [Egress and secrets](https://agenthold.dev/egress/) explains the model.
- **Shared and audited.** Workspaces, roles, invitations and an audit log let a team use the same agents. See [Sharing and audit](https://agenthold.dev/sharing/).
- **Scriptable.** Everything the UI does is in the [HTTP API](https://agenthold.dev/api/), and [tokens, schedules and webhooks](https://agenthold.dev/automation/) drive it from scripts. Agents can call each other.

Try it at [demo.agenthold.dev](https://demo.agenthold.dev), or run your own.

- **Install** — A Linux server with Docker, a domain and a way to sign in.
- **Sessions and harnesses** — How chats work, and how Claude Code and Codex logins are set up.
- **Security** — The threat model and what each layer protects.
- **API reference** — Every endpoint, generated from the OpenAPI spec.

Source: https://agenthold.dev/index.mdx