Hax: A Minimalist Terminal-Native Coding Agent in C
Hax is a minimalist, terminal-native coding agent written in C. It ships as a single native binary with minimal dependencies, starts instantly, and uses only a few MB of RAM — leaving more memory for your local LLMs.
Key Features
- 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. Example:
llama-server -m [model].gguf
hax --provider llama.cpp
-p one-shot mode with resume hints on stderr, plain-text config and session files, composition via subprocesses instead of plugins.Who It's For
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 explains each omission.
Getting Started
Hax runs on Linux and macOS; on Windows, use it under WSL. Install with Homebrew:
brew install oleksandrchekhovskyi/hax/hax
On Arch Linux, hax is in the AUR as hax. On any Linux, download the prebuilt static binary (x86_64 or aarch64) from the latest release and put it on your PATH.
Build from source:
git clone https://github.com/OleksandrChekhovskyi/hax.git
cd hax
scripts/install_deps.sh # Debian/Ubuntu, Fedora, Arch, openSUSE, Alpine, macOS
make # binary at ./build/hax
make install # optional; may prompt for sudo
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 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 for provider setup and full documentation.
📖 Read the full source: HN AI Agents
👀 See Also

OpenClaw Local Agent Implementation with TurboQuant Caching for Mid-Range Hardware
A one-click app for OpenClaw with local models now runs on mid-range devices like MacBook Air with 16GB RAM using TurboQuant caching and context warming. The implementation patches llama.cpp for reliable tool calling and achieves 10-15 tokens per second with Gemma 4 and QWEN 3.5.

ArayCode: Desktop CLI Client for OpenClaw with Voice, Multi-Agent Hotkeys, and Markdown UI
ArayCode turns OpenClaw into a desktop CLI app with voice I/O, multi-agent hotkeys, themes, and markdown UI built on Spectre.Console. Supports cloud and local STT/TTS providers.

Claude IDE Bridge: MCP Tool for Remote Editor Access
Claude IDE Bridge is an open-source tool that provides Claude AI with remote control access to code editors via MCP (Model Context Protocol). It exposes editor knowledge like live type information and debugger state as callable tools.
Bend: A Proof-Checked Language That Blocks AI Mistakes on CPU and GPU
Bend compiles to native code and runs in parallel across CPU cores or GPU. Its LAWS.bend files let agents prove rules hold, blocking bug merges before they happen.