This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
hax
A minimalist, terminal-native coding agent written in C
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.
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.
About hax on Product Hunt
“A minimalist, terminal-native coding agent written in C”
hax was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #152 on the daily leaderboard. 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.
On the analytics side, hax competes within Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1M followers on Product Hunt. The dashboard above tracks how hax performed against the three products that launched closest to it on the same day.
Who hunted hax?
hax was hunted by Oleksandr Chekhovskyi. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of hax including community comment highlights and product details, visit the product overview.
Oleksandr Chekhovskyi
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.