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

How to keep AI coding sessions running through SSH drops with Session Kit

Start Claude Code or Codex on a remote host and reconnect later without losing the session.

Who it is forA developer who runs AI coding agents on a remote Linux host and works from a laptop over SSH that sometimes drops.

The problemWhen the SSH connection or terminal closes, the agent session in that window is lost or hard to find again.

The outcomeSessions keep running on the host. After reconnecting, you open the picker and type the number of the session you want.

What you need first

  • Linux with systemd, or macOS 14 or newer
  • shpool 0.11.0, the stock build
  • Claude Code, Codex, or both
  • One trusted Unix account with per-user service access
  • Python 3.10+ on Linux or Python 3.11+ on macOS, plus Bash 4+

Steps

  1. On the remote host, install Session Kit for your user following the README.
  2. Run sp new claude or sp new codex to start a session on the host.
  3. Close your terminal or let the SSH connection drop. The session keeps running on the host.
  4. Reconnect over SSH and run kit.
  5. Type the session number to return to the session.

Prompt for your agent

On the remote host <host>, install Session Kit from https://github.com/dob323/session-kit using the latest release artifact, run `session-kit services enable`, then start a session with `sp new claude`. Verify with `kit` that the session is listed and still running after the SSH connection is closed and reopened.

Caveat. Session Kit runs on a Linux or macOS host with systemd or launchd services, so a host without those will not work as described.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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