hax

Lightweight by design - starts instantly and uses only a few MB of memory. Local models are first-class - auto-discovers config from running llama-server. Respects your terminal - native scrollback is preserved. Inspectable - See exact model-facing conversation a usable transcript view. Broad provider support - OpenAI, Anthropic, Codex, OpenRouter, OpenCode Zen/Go, llama.cpp, and more. Well-behaved Unix tool - XDG paths, plain text input/output, composition via subprocesses instead of plugins.