Files
hermes-agent/plugin-catalog/woof.yaml
teknium1 b9204ea975 feat(plugin-catalog): add woof
WOOF weather simulations on your own NVIDIA GPU (recastsystems/hermes-woof @ 2c82b34). Requested by community member drewsny.
2026-10-01 10:46:10 -07:00

30 lines
1.4 KiB
YAML

name: woof
repo: https://github.com/recastsystems/hermes-woof
sha: 2c82b34eb386a490d25439757556f6bab84048af
description: "Plan, launch, watch and compare WOOF weather simulations on your own NVIDIA GPU: size runs with WOOF's own planner, launch them locally or on an ssh/WSL GPU host, get maps in the chat while the forecast runs, compare physics or resolution, run multi-arm research campaigns and score runs against radar and surface observations. Disclosure — runs need Linux x86_64 with an NVIDIA GPU (plan-only elsewhere); the user-run hermes woof install pip-installs recast-woof>=1.0.0,<1.1 into ~/woof-env and downloads WOOF tables and optional geography (about 1.6 GB); runs execute the WOOF CLI as detached background jobs writing to ~/woof-runs and fetch public weather data; run events are pushed into the chat as user-role messages; the optional serve/ scripts download llama.cpp and a Qwen GGUF and start an unauthenticated local model server."
maintainer: recastsystems
tier: community
category: tools
version: "0.1.0"
docs_url: https://github.com/recastsystems/hermes-woof#readme
capabilities:
provides_tools:
- woof_doctor
- woof_catalog
- woof_docs
- woof_plan
- woof_launch
- woof_status
- woof_stop
- woof_show
- woof_compare
- woof_campaign
- woof_score
- woof_report
provides_hooks:
- pre_llm_call
- post_llm_call
- on_session_end
provides_middleware: []
requires_env: []