Hax – a minimalist, terminal-native coding agent written in C

OleksandrChekhovskyi released hax, a minimalist terminal-native coding agent written in C, which starts instantly and uses only a few MBs of RAM to leave more memory for local LLMs. The tool supports local models via llama.cpp, OpenAI, Anthropic, Codex, OpenRouter, and other providers, and is available for Linux and macOS via Homebrew or prebuilt static binaries. Hax targets developers who prefer lightweight, inspectable Unix-style tools over plugin-heavy agents.

Lightweight by design A single native C binary with a small dependency set. Starts instantly, and uses a very small amount of memory just a few MBs — so more RAM is left for your local LLMs. Local models are first-class hax auto-discovers the model and runtime capabilities. No custom provider config block needed for the default setup. llama-server -m model .gguf hax --provider llama.cpp Respects your terminal Streaming Markdown and live tool output, reflowed for display in the terminal. Only redraws the current streaming line or the input area, native scrollback is preserved. Does not take over or mess with your terminal. Inspectable See exactly what was sent to the model and what it replied in a usable transcript view Ctrl+T . Optionally collect a detailed wire protocol trace. Use any provider/model Supports OpenAI +compatible , Anthropic +compatible , Codex via ChatGPT subscription , OpenRouter, llama.cpp, etc. Well-behaved Unix tool XDG paths, clean stdout in -p one-shot mode with resume hints on stderr, plain-text config and session files, composition via subprocesses instead of plugins. Target audience Developers who live in the terminal, run local models, audit what their tools do, package software for distros, or run agents where resources are scarce. If you want MCP marketplaces, a plugin runtime, IDE panels, or per-command permission prompts, other agents build exactly that — hax deliberately doesn't, and docs/philosophy.md https://github.com/OleksandrChekhovskyi/hax/blob/master/docs/philosophy.md explains each omission and the pattern that covers the need. If "fancy new AI tech in an old-school minimalist package" sounds like your vibe, you might like this. $ Get started hax runs on Linux and macOS; on Windows, use it under WSL https://learn.microsoft.com/en-us/windows/wsl/ . With Homebrew https://brew.sh macOS or Linux : brew install oleksandrchekhovskyi/hax/hax On Linux, download the prebuilt static binary for your architecture x86 64 or aarch64 from the latest release https://github.com/OleksandrChekhovskyi/hax/releases/latest , then unpack the hax binary into any directory on your PATH . Building from source gives a binary linked against your system's shared libraries instead of a static one: git clone https://github.com/OleksandrChekhovskyi/hax.git cd hax scripts/install deps.sh Debian/Ubuntu, Fedora, Arch, openSUSE, Alpine, macOS make the binary is now at ./build/hax make install optional; may prompt for sudo scripts/install deps.sh installs the build dependencies — a C compiler, libcurl, jansson, meson, ninja, and pkg-config — plus fzf , which hax uses for @file completion when available. Run hax from the project directory you want it to work in: hax interactive REPL hax -p "list TODOs" run one prompt and print the final answer printf "explain x" | hax -p read the prompt from stdin hax -c continue the latest session for this directory hax --resume pick a past session for this directory hax --resume=ID -p "next" resume a specific session in one-shot mode The easiest first run is interactive: start hax , then use /provider to see available providers and choose a model. hax remembers interactive provider, model, and effort selections. See the README https://github.com/OleksandrChekhovskyi/hax readme for provider setup and the full documentation.