Menu
Start the local LLM server for the clarus explain step. Use when Dispatch Brief generation fails or when the explain stage is needed in the demo.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Run the clarus end-to-end demo pipeline (14 stages) or the document compliance / maritime security demos. Use when verifying the full pipeline or preparing a demo for reviewers.
Run the clarus Tauri desktop application locally. Use when developing or testing the GUI.
Set up clarus development environment — Rust toolchain, Node.js, Tauri CLI, and edgesentry-rs sibling checkout. Use when onboarding a new machine or when the build environment is broken.
| name | clarus-llm-setup |
| description | Start the local LLM server for the clarus explain step. Use when Dispatch Brief generation fails or when the explain stage is needed in the demo. |
| license | Apache-2.0 |
| compatibility | Requires llama.cpp installed (brew install llama.cpp on macOS) |
| metadata | {"repo":"clarus"} |
cd scripts && ./run_llama.sh
Starts llama-server at http://localhost:8080.
Default model: bartowski/Llama-3.2-3B-Instruct-GGUF
Then pass --llm-url http://localhost:8080 to eds explain run.