LocalLLM

experimentalai

Local LLM inference via Ollama (primary) or llama.cpp (fallback)

pip install chp-adapter-local-llm

Auto-discovered through the chp.adapters entry point — no host config needed.

Capabilities

What this adapter exposes.

chatv1.0.0

Multi-turn chat with message history. Messages are NOT recorded in evidence.

chp.adapters.local_llm.chat

generatev1.0.0

Single-turn text generation. Prompt and completion are NOT recorded in evidence.

chp.adapters.local_llm.generate

list_modelsv1.0.0

List models available in the local LLM backend.

chp.adapters.local_llm.list_models

model_infov1.0.0

Get metadata for a specific model (parameter count, context length, quantization).

chp.adapters.local_llm.model_info