llm/

Package claude implements llm.Runner by invoking the Claude CLI.

Package embed is the local host's embed.Embedder composition: it resolves model.EmbeddingConfig — a host-private schema that never goes public — into one pkg/llm/embed Embedder (provider adapter, timeout, rate limit), paralleling the chat-runner factory.

Package factory is the local host's llm.Runner composition: it resolves model.LLMConfig — a host-private config schema that never goes public — into one composed pkg/llm Runner (provider adapter, rate-limit decorator, timeout decorator).

Package gollm implements llm.Runner on top of github.com/teilomillet/gollm, providing a unified adapter for Anthropic API, OpenAI, Ollama, and other providers supported by gollm.