llm_backendslisted

# llm_backends — Local LLM discovery, audit & routing Turn idle local hardware into a token-saving tier. Every task served by a local model is a task **not** billed to the cloud. ## When to use - The user mentions **LM Studio, Ollama, LocalAI, vLLM, llama.cpp**, "local model", "run it locally", or "use my GPU". - You need to know **what models are reachable** (this machine or the network). - A task is cheap/local-suitable (classification, extraction, short summary, routing, spell-check, simple Q&A) and could skip the cloud entirely. - The user has **no** local model yet and wants step-by-step, hardware-aware setup. ## Quick commands ```bash # Discover + register backends (writes configs/llm-endpoints.json) python -m skills.llm_backends.cli scan # localhost only python -m skills.llm_backends.cli scan --subnet # sweep local /24 python -m skills.llm_backends.cli scan 192.168.1.47 # specific host(s) # What's registered? python -m skills.llm_backends.cli list # Audit: are local models used? what can this machine run? next steps? python -m skills.llm_backends.cli audit --fresh # Run a prompt locally (0 cloud tokens) python -m skills.llm_backends.cli chat "classify: bug or feature?" --max-tokens 128 # Suggest a local model for a project (adaptive per project type) python -m skills.llm_backends.cli profile ~/my-project ``` ## Programmatic use ```python from skills.llm_backends import registry, quick_chat, audit registry.refresh()