hax icon
hax icon

hax

 11 likes

A minimalist, terminal-native coding agent. A single native C binary that uses a few MBs of RAM. Local models are first-class via llama.cpp and Ollama; also OpenAI, Anthropic, OpenRouter, and Codex.

hax screenshot 1

Cost / License

  • Free
  • Open Source (MIT)

Application type

Since

  • Since 2026

Updated

  • Updated Nov 2026

Releases

  • 8 releases last year8 last year

Platforms

  • Mac
  • Linux
  • BSD
  • FreeBSD
  • OpenBSD
  • Homebrew
11likes
0articles
Save

Features

Properties

Features

Highlights All activities

hax News & Activities

Recent activities

  • Abdulmajid-Yunusov liked hax
  • kirill0ermakov liked hax
  • TheGitAI icon
    TheGitAI added hax as alternative to TheGitAI
  • Reika icon
    alexwkleung added hax as alternative to Reika
  • Memdoor icon
    Grego-Avaux added hax as alternative to Memdoor
  • Superpowers by Obra icon
    Croco Loki added hax as alternative to Superpowers by Obra
  • Thurbox icon
    Alaik added hax as alternative to Thurbox
  • April Dudley liked hax
  • Vaneesa Lenz liked hax
  • Claude Code icon
    oleksandr_chekhovskyi added hax as alternative to Claude Code and Pi Agent

hax information

AlternativeTo Categories

AI Tools & Services, Development

GitHub repository

  •  1,001 Stars
  •  71 Forks
  •  22 Open Issues
  •   Updated  
View on GitHub

Our users have written 1 comment or review about hax, and it has gotten 11 likes.

hax was added to AlternativeTo by Paul on and this page was last updated .

Comments and Reviews

   
Viktor Korobov
0

I really appreciate this kind of minimalism. A fast, lightweight coding agent that simply works in the terminal without unnecessary layers is refreshing. Sometimes less really is more.

Official Links

What is hax?

A minimalist, terminal-native coding agent written in C.

Key features:

  • Lightweight by design — A single native C binary with a small dependency set. Starts instantly, and uses very small amount of memory (just a few MBs) - so more RAM is left for your local LLMs.
  • Local models are first-class — Start llama-server -m [model].gguf, then hax --provider llama.cpp, and hax auto-discovers the model and runtime capabilities. No custom provider config block needed for the default setup.
  • 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.