hax
A minimalist, terminal-native coding agent written in C
What it does
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.
A single native C binary using only a few MB of RAM. Local models are first-class; supports OpenAI, Anthropic, Codex, OpenRouter, and OpenCode Zen/Go.
A single native C binary with a small dependency set. Starts instantly and uses only a few MB of memory, leaving more RAM for local models. hax auto-discovers the model and runtime capabilities. No custom provider config block is needed for the default setup. llama-server -m [model].gguf hax --provider llama.cpp > 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. 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…from usehax.dev
Does the same job
all alternatives →
- NONous – Open-Source Agent Framework with Autonomous, SWE Agents, WebUI2024 · github.com · ▲155
Hello HN! The day has finally come to stop adding features and start sharing what I've been building the last 5-6 months. It's a bit of CrewAI, OpenDevon, LangFuse/Cloud all in one, providing devs who prefer TypeScript an integrated framework thats provides a lot out of the box to start experimenting and building agents with. It started after peeking at the LangChain docs a few times and never liking the example code. I began experimenting with automating a simple Jira request from the engineering team to add an index to one of our Google Spanner databases (for context I'm the…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com