Kule needs testers: run AI agents on a copy of your folder, then tell me what broke

Описание и применение

Kule – это инструмент для безопасной работы AI‑агентов с папками. Автор просит пользователей протестировать его на собственных машинах, сообщая о неожиданных результатах, чтобы улучшить политику и изоляцию.

Задача

Kule is a new open‑source control room for AI agents that work on folders, but the author needs real‑world testing to validate its safety and usability.

Результат

The author invites users to run Kule on their own machines, report unexpected behavior, and help refine policies and sandboxing. Early feedback will drive fixes in subsequent previews.

Рабочий процесс

• 1. Install Kule via the install guide.
• 2. Create a test folder or use a committed project.
• 3. Run one of the six testing scenarios (install check, loop without agent, app with agent, own work, own setup, boundaries).
• 4. Observe the sandboxed actions, policy prompts, and terminal output.
• 5. Report findings by opening a GitHub issue (Bug report, Test report, or Idea).

Доказательства

Kule is a control room for AI agents that work on your folders. You point an agent (Claude Code, Codex, Gemini, or any agent that speaks ACP) at a folder.

Источник

The default policy is an allow‑list now.

Источник

Nothing an agent writes reaches your home.

Источник

Your terminals run in the task's sandbox too, not just the agent.

Источник

I wrote a short testing guide with six scenarios.

Источник