kam

Lm — AI skill for Claude Code

AI community

Point hamster's local-model slot at whatever you run — oMLX, LM Studio, Ollama, llama.cpp, or any OpenAI-compatible server — and pick a fast and a quality model.

How to install Lm

Installs to ~/.claude/skills/kam-hamster-lm/SKILL.md

Terminal

mkdir -p ~/.claude/skills/kam-hamster-lm && curl -fsSL https://raw.githubusercontent.com/kam/hamster/HEAD/commands/lm.md -o ~/.claude/skills/kam-hamster-lm/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Lm does

description: Point hamster's local-model slot at whatever you run — oMLX, LM Studio, Ollama, llama.cpp, or any OpenAI-compatible server — and pick a fast and a quality model. Saved in ~/.claude/hamster/config.json; keys are never stored. argument-hint: [detect | show | test | clear]

The local-model slot drafts summaries, error clusters and the "worth remembering?" verdict at zero API tokens. Order: configured server → Apple on-device (macOS 26+) → the in-session model. This command sets

Alternatives in AI

Repomix — 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file 22.7k ★
Inference Serving — ai-research-skills vLLM, SGLang, TensorRT-LLM, llama.cpp 5.4k ★
Internal Safety Collapse — We built an adversarial codespace setup 1.2k ★