Hacker News: OleksandrC

New comment by OleksandrC in "Codex CLI installs a persistent, self-updating background daemon by default"

OleksandrC — Mon, 12 Oct 2026 19:58:49 +0000

(author passing by) Could you please report the issues you've experienced on the repo? I did quite a bit of testing myself on local models (Qwen, Ornith, Gemma, Muse Glimmer) with llama.cpp, and they all worked fine. Details would be helpful.

Also one brief note for Codex users specifically. hax can work out-of-the-box as codex-cli drop-in replacement (since it can use the already authenticated codex token), so it's super easy to try it - basically it will be a zero-config experience.

New comment by OleksandrC in "A Modern Web App in C"

OleksandrC — Mon, 12 Oct 2026 17:12:07 +0000

For people who find interest in weird web applications, I have been working on a game project, in C++, where the client is compiled to WebAssembly with Emscripten, and the application server is also implemented in C++ (behind nginx).

This is from pre-AI era also. The game is Civ-like. Custom engine from scratch (including both the 3D stuff, and all the web handling also).

Take a look: https://statebuilder.com/

New comment by OleksandrC in "You Said No MCP"

OleksandrC — Wed, 30 Sep 2026 10:34:00 +0000

Honestly, the provided argument for it is rather weak. They are basically adding a way of running scripts that are contained within harness to execute harness's own tools (that's the Codemode). A coding agent can already compose any arbitrary logic by invoking shell scripts (or python scripts, or node scripts), etc - so this is just entirely unnecessary in the core, from my perspective.

If you feel that Pi has been drifting away from its original vision, try hax (https://usehax.dev/) - you might like it.

New comment by OleksandrC in "Nine coding harnesses vs. your laptop"

OleksandrC — Fri, 11 Sep 2026 06:36:12 +0000

If you're looking for a coding agent that would fit nicely into resource-constrained environments (such as laptops, or tiny VPS servers, or tiny single-board computers, etc), and would also work great with local models - you might also like hax (https://usehax.dev/). 0.7 MB dynamically linked native C binary, few MBs of RAM usage when running, auto-discovers config from running local llama-server, and uses minimalist system prompt and tools for lean context usage.

New comment by OleksandrC in "fx :Tiny, open, native coding agent."

OleksandrC — Thu, 20 Aug 2026 08:56:03 +0000

Technically, this would be straightforward. The problem is that Anthropic seems to be really against using Claude subscriptions with anything other than Claude Code - you might even risk your account getting banned for doing so. You could search online for the "openclaw claude banned" for more details on that story.

New comment by OleksandrC in "Feature Request: Support AGENTS.md"

OleksandrC — Wed, 19 Aug 2026 22:58:31 +0000

The obvious reason is that they would prefer to have CLAUDE.md files in every repo (even if it's just a symlink to AGENTS.md). It serves as a free advertisement for them. Same reason as for auto-adding attribution text in commit messages, etc. It's the "Sent from my iPhone" of our time.

New comment by OleksandrC in "fx :Tiny, open, native coding agent."

OleksandrC — Wed, 19 Aug 2026 21:11:03 +0000

If you like this list of "why?", you might also like this: https://usehax.dev/ (I am the author). Most of the list applies, similar minimalist Unix tool approach, with some differences. Hax is written in C, the dynamically linked binary is even smaller (0.6 MB), MIT-licensed. No wasm though.

Important difference - fx is currently Vercel AI Gateway only - while hax does support multiple providers already (OpenAI API, ChatGPT/Codex subscription, Anthropic API, OpenRouter, OpenCode Zen/Go), and integrates well out of the box with local llama-server.

New comment by OleksandrC in "OpenRouter is joining Stripe"

OleksandrC — Wed, 19 Aug 2026 18:39:14 +0000

I am working on my own agent implementation (https://usehax.dev/), and I can praise OpenRouter for being seemingly the only provider endpoint that actually gives proper API for gathering available models and their capabilities (context length, image support, pricing, etc), reports exact routing details and total cost in the response, and provides an endpoint for obtaining current available credits (for "/usage"-like command). So for OpenRouter specifically I could deliver a really good experience out-of-the-box (always fresh models and metadata, exact pricing, etc).

You would think that these things would be standard fare, but they really are not. Other providers need metadata from a separate catalog, don't report pricing, don't really report available credits / usage either.

So yes, OpenRouter does have a good DevEx.

New comment by OleksandrC in "Hax – a minimalist, terminal-native coding agent written in C"

OleksandrC — Wed, 12 Aug 2026 19:04:20 +0000

As usual, I suppose :) - by filing bug reports, and opening pull requests.

New comment by OleksandrC in "Hax – a minimalist, terminal-native coding agent written in C"

OleksandrC — Wed, 12 Aug 2026 17:56:36 +0000

Generally, the models seem to adapt really well. I am using GPT models in hax a lot, and they have no trouble whatsoever using hax tools instead of their "native" codex tools.

Also since hax tools are just "read", "edit", "write", "bash" and "task_wait", it would be expected that the models would use one-off scripts to achieve their goals (either shell scripts, or python scripts, etc).

New comment by OleksandrC in "Hax – a minimalist, terminal-native coding agent written in C"

OleksandrC — Wed, 12 Aug 2026 17:51:48 +0000

The main reason to use C is that it's the easiest way to achieve minimal resource footprint. Also it's the language I know really well already.

The demo was recorded with asciinema.

Hax – a minimalist, terminal-native coding agent written in C

OleksandrC — Wed, 12 Aug 2026 14:43:45 +0000

Article URL: https://usehax.dev/

Comments URL: https://news.ycombinator.com/item?id=49273175

Points: 121

# Comments: 36

New comment by OleksandrC in "Show HN: Ante, a coding agent in a single binary that runs offline"

OleksandrC — Mon, 10 Aug 2026 17:30:22 +0000

I will leave this here: https://usehax.dev/ GitHub repo: https://github.com/OleksandrChekhovskyi/hax

This is a coding agent implementation I am working on, which delivers what this promises (at least on the "lean" part), except it's actually fully open source, and even more lean (few MBs of runtime memory usage).

MIT-licensed, written in C, multi-provider / multi-model, minimalist approach to system prompt and tools (think kinda like pi, but with a bit more "batteries included", like subagents and background tasks out of the box), polished presentation, inspectable (usable transcript view), etc.

New comment by OleksandrC in "Pi's Minimalism Is Its Advantage"

OleksandrC — Wed, 05 Aug 2026 09:56:23 +0000

I am working on an agent implementation that you might like: https://github.com/OleksandrChekhovskyi/hax

Written in C, tiny footprint, minimalist approach to system prompt and tools (yet essential batteries are included, for example - it has subagents with presets, and background bash tasks out of the box), high quality polished presentation, inspectable (usable transcript view), does not mess with terminal scrollback, respects XDG directory spec, etc.

Open source, MIT-licensed, no commercial agenda. A tool that I myself wanted, so I built it.

New comment by OleksandrC in "Back to Kagi"

OleksandrC — Wed, 22 Jul 2026 14:42:50 +0000

This would be an interesting use case. But it seems API access is not included in the subscription? The value proposition would have been higher if it was (so one subscription for both human and agent use).

New comment by OleksandrC in "Codeberg bans vibe coded projects"

OleksandrC — Wed, 22 Jul 2026 09:37:57 +0000

They could, for example: 1. Rely on users flagging suspected repos (with human moderators reviewing afterwards). 2. Deploying AI agents to evaluate repos against known AI-generated-code patterns (also with human moderators afterwards). Of course, the irony of the situation - using slop machines to fight slop.

New comment by OleksandrC in "Codeberg bans vibe coded projects"

OleksandrC — Wed, 22 Jul 2026 09:27:01 +0000

Claude-written code is quite easy to spot - because it has this particular style of overly verbose "walls of text" comments, that 1. repeat verbatim what the code just below does, 2. include "list of things" that quickly go stale, 3. talk about "how things used to be before we changed it here" (useless to anyone reading the code now), 4. "talk to reviewer" in comments. And many other comment sins.

And even if you tell it to make it leaner, it'll maybe trim a little, but it'll still be a wall of text. Claude really likes to write its opuses and fables in comments.

And commit messages suffer from the same verbose prose.

And all of that happens even if you explicitly instruct in CLAUDE.md to keep things lean/concise. It's a disease.

New comment by OleksandrC in "The Growing Compute Shortage"

OleksandrC — Tue, 21 Jul 2026 12:02:58 +0000

Recent Kimi K3 release is supposedly frontier-grade, so would be interesting to see what it really costs to run inference for models of this class, when the weights get released and other independent providers pick it up (then we could reasonably expect competitive pricing with low-ish margins).

New comment by OleksandrC in "Ask HN: Claude Code or Codex?"

OleksandrC — Tue, 21 Jul 2026 10:01:51 +0000

One significant advantage of Codex subscription over Claude is that you can use any agent harness with it. Meanwhile Anthropic insists that Claude subscription must only be used with Claude Code itself - and I have significant gripes with the quality of Claude Code in general.

Also, Fable access was now removed from small 20$ Claude plan, while Codex includes access to comparable model (gpt-5.6-sol) even on small subscription.

New comment by OleksandrC in "Who's afraid of Chinese models?"

OleksandrC — Mon, 20 Jul 2026 21:57:21 +0000

The article makes a point about agent harnesses being sticky (the supposed moat). I have been building my own agent harness for a while, and I can tell with confidence that the harness almost does not matter, the entirety of the AI magic is the model itself. The harness can be almost barebones (like, for example, mini-swe-agent used for benchmarks), and yet the model still does the task just fine.

So from my perspective, it's doubtful that this is the moat. Besides, for example, Claude Code in particular is so buggy (and always has been).