Back to directory

hax

A minimalist, terminal-native coding agent written in C, distributed as a single small binary, built for developers who run local models and want to audit exactly what their tools do.

hax

hax is a coding agent written in C as a single native binary with a small dependency set, aimed at developers who live in the terminal, run local models, audit their tools, or package software for a Linux distribution. It starts instantly, leaves more memory available for local models, and only redraws the current streaming line or input area so a terminal's native scrollback stays intact.

It auto-discovers a running llama-server instance for local models with no extra configuration, and also supports OpenAI, Anthropic, Codex through a ChatGPT subscription, OpenRouter, OpenCode Zen or Go, and custom endpoints. A transcript view shows exactly what was sent to and received from a model, and the project deliberately omits MCP marketplaces, a plugin runtime, IDE panels and per-command permission prompts, leaving those to other agents. It runs on Linux, macOS, FreeBSD, OpenBSD, and under WSL on Windows, installable through Homebrew, the AUR, a static binary, or building from source.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.