Remote Compute: SSH

SkillMonitoring & ops

Your AI can run research jobs on remote machines, including Slurm clusters, lab hosts, and GPUs, by connecting over SSH. It handles the setup on the remote machine, submits the job, and collects the logs and results when the work is done. That means heavy research tasks can run where the computing power is instead of on your local machine.

Available today. Use it from your connected AI after setup.

Add the skill, then ask your AI to run a job and tell it which machine to use. It connects over SSH, runs the job, and brings back the logs and results.

Then ask your AI: use the Remote Compute: SSH skill

What your AI can do with it

  • Run research jobs on remote SSH, Slurm, or lab machines
  • Set up a remote host before a job runs
  • Submit jobs to a Slurm cluster
  • Collect logs from finished jobs
  • Sync artifacts and results back from the remote machine
  • Run work on GPU and cluster machines

What this skill tells your AI

The instructions your AI receives, as published by companion-inc/feynman in skills/remote-compute-ssh/SKILL.md and read by ahel’s review.

Use this skill for lab machines, SSH hosts, and Slurm-style research jobs.

Workflow:

  1. Record host alias, scheduler, working directory, environment module/conda/container needs, data paths, and artifact return path.
  2. Verify access and a tiny smoke command before the main job.
  3. Submit with a bounded script that logs package versions, hardware, command, and seed.
  4. Harvest stdout/stderr, job id, exit status, produced artifacts, and checksums into the Feynman workspace.
  5. Mark failed or partial jobs honestly; do not fabricate remote artifacts from local expectations.

Keep remote credentials and private paths out of user-facing summaries unless they are needed for reproducibility.

Signals

GitHub stars
9k
Forks
1k
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
remote-compute-ssh
Source
github.com/companion-inc/feynman