hax
A minimalist, terminal-native coding agent written in C
3 followers
A minimalist, terminal-native coding agent written in C
3 followers
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.
Free
Launch Team
Viktor.comAn AI coworker that actually does the work
Promoted
Today most of the coding agent implementation are bloated kitchen sinks of disjointed features, consuming hundreds of MBs of memory, a lot of CPU time, and wasting LLM context windows with excessive system prompt and built-in tools, while often delivering subpar user experience on the expected core agent functionality.
hax was created in adherence to Unix philosophy, it strives to "do one thing, and do it well", cuts unnecessary features ("less is more"), and is extensible by giving the agent more Unix tools in the environment instead of building a plugin runtime.
It is implemented in old-school portable C, dynamically linked binary is ~0.7 MB, consumes a few MB of private memory while running, while implementing enough of the functionality to be a comfortable daily driver.