coldpass

molssi-ai/xnn

GitHub ↗ · How this check works

Per-setup public labels: Linux / Haiku: Works

Static status badge · SVG · read-only JSON. Embed with ![Coldpass status](https://coldpass.dev/badge/molssi-ai--xnn.svg).

force-fieldsmachine-learning-interatomic-potentialsmaterialsmlipmoleculesconvolutional-neural-networks

Works

Only older checks are saved; no current product test.

Answers apply to each recorded setup, revision and operation. Earlier observations remain in Run details.

Tested on Linux
PlatformHaikuLuna
Linuxyes

Linux / Haiku 5.5: yes · Oct 18, 2026 · 4458d833d032 · claude-code / 2.1.300 (Claude Code)
Recorded operation: /tmp/xnnvenv/bin/python examples/quickstart.py

Needs keys or browser
None seen
Setup time
3 min 12 s to install, 16 s to first use
Issue
none found in recorded check

Safety: no observations were recorded for the selected revision. Functional results do not establish a safety result.

Run details

Haiku 5.5

Native agent · Checked operation passed

Checked operation /tmp/xnnvenv/bin/python examples/quickstart.py

Agent-reported scope: Ran the README's documented example `python examples/quickstart.py`: builds a toy dataset, trains a SchNet model for 3 epochs with the Trainer, then runs inference returning energy and forces (shape (5,3)).

Run details
run
molssi-ai--xnn-claude-haiku-5-5-1792336013293039160
date
Oct 18, 2026
time to working
232.8s
product hosting / execution
Local command in the guest
recorded operation scope
product operation
model
claude-haiku-5-5
agent / version
claude-code / 2.1.300 (Claude Code)
platform
linux
reported cost
$0.004691
Recorded source
https://github.com/molssi-ai/xnn
Tool transport
mcp-assigned-vm
Test version
readme-d82246e0bbc037649a4db516d4aa456c0500644302d6c13970f8d8766d8bd681
revision
4458d833d032e206674a1e3c5d53843924f38d23
Whose fault: not assigned · resolved

What the agent did

Ran the README's documented example `python examples/quickstart.py`: builds a toy dataset, trains a SchNet model for 3 epochs with the Trainer, then runs inference returning energy and forces (shape (5,3)).

apt-get install -y python3-venv (guest only had python3)
python3 -m venv /tmp/xnnvenv
/tmp/xnnvenv/bin/pip install xnns  (README Installation: pip install xnns; installed xnns 0.15.0)
/tmp/xnnvenv/bin/xnn  (confirmed CLI: train, benchmark, export, mdi, models)
/tmp/xnnvenv/bin/python examples/quickstart.py  (README 'Examples and tests'; exit 0)

run JSON · checker evidence · agent report + check · transcript excerpt · error excerpt