Modal Compute
SkillCloud & infraThis skill lets your AI run research benchmark and replication jobs on remote GPU computers through Modal. When a Feynman research workflow needs extra GPU power, your AI can write a Python script and send the job to run remotely. The Modal CLI needs to be available for this to work.
Available today. Use it from your connected AI after setup.
No other account needed.
Make sure the Modal CLI is available, then ask your AI to run a benchmark or replication job as part of your Feynman research workflow.
Then ask your AI: use the Modal Compute skill
What your AI can do with it
- Run research benchmark jobs on remote GPU computers
- Run replication scripts to reproduce research results
- Write the Python scripts that launch jobs on Modal
- Add burst GPU compute when a Feynman research workflow needs it
What this skill tells your AI
The instructions your AI receives, as published by companion-inc/feynman in skills/modal-compute/SKILL.md and read by ahel’s review.
Use the modal CLI for bounded research experiments that need burst GPU compute. No pod lifecycle to manage; write a decorated Python script, run it, and save raw outputs back into the research artifact folder. Do not use this skill to deploy services or unrelated batch jobs.
Setup
pip install modal
modal setup
Commands
| Command | Description |
|---|---|
modal run script.py | Run one research experiment script on Modal |
modal run --detach script.py | Run a long research experiment and record the returned app/run identifier |
modal shell --gpu a100 | Open an interactive GPU shell for research environment debugging |
GPU types
T4, L4, A10G, L40S, A100, A100-80GB, H100, H200, B200
Multi-GPU: "H100:4" for 4x H100s.
Script pattern
import modal
app = modal.App("experiment")
image = modal.Image.debian_slim(python_version="3.11").pip_install("torch==2.8.0")
@app.function(gpu="A100", image=image, timeout=600)
def train():
import torch
# training code here
@app.local_entrypoint()
def main():
train.remote()
When to use
- Bounded replication or benchmark jobs that need burst GPU
- No persistent state needed between runs
- Check availability:
command -v modal
Signals
- GitHub stars
- 10k
- Forks
- 1k
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
modal-compute- Source
- github.com/companion-inc/feynman