DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to have an AI assistant diagnose a live SSH session with Hatoba

Let a model read your terminal and run approved commands on a server, with control over each action.

Authorization notice. Hatoba is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Credentials. The assistant sends the screen, attachments, and tool results to the model provider, so host addresses, passwords, and keys on screen reach that provider.

Who it is forAn engineer debugging a failing server who wants help reading logs and running checks without typing each command by hand.

The problemTracing a fault across logs, processes, and config files takes many small steps, and copying output into a chat tool is slow and loses context.

The outcomeThe assistant reads the terminal, proposes or runs commands with your approval, and reports the likely cause.

What you need first

  • A computer running Windows, Linux, or macOS (Windows is the maintainer's main platform)
  • Rust stable, Node.js 22 or later, and pnpm for building from source
  • WebView2 on Windows, Xcode Command Line Tools on macOS, or the Tauri system dependencies such as libwebkit2gtk-4.1-dev on Linux
  • SSH access to at least one host, with a password or key
  • A Cloudflare account for optional sync (the free plan usually covers personal use)
  • An API key from an OpenAI-compatible or Anthropic provider for the AI assistant

Steps

  1. Add your OpenAI-compatible or Anthropic API key in Settings.
  2. Open an SSH connection to the failing host and open the AI assistant panel beside the terminal.
  3. Describe the problem, and choose Approve each action, Auto mode, or bypass mode based on how much control you want to keep.
  4. Review every command the assistant proposes before it runs, and stop it if the output looks wrong.
  5. Ask for a summary of the findings and the changes it made.

Prompt for your agent

In the scarletkc/Hatoba app, open an SSH session to <host>, ask the AI assistant to find why <service> is failing, and keep approval on for every action. Verify that the assistant lists each command it ran and that you approved each one before execution.

Caveat. The README says the assistant sends the terminal screen with each message unless you turn that off, so clear sensitive output or disable that setting before debugging on a host with secrets visible.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page