Plainspeak
A Voice layer for AI agents to write like a human.
What it does
We are fed up with unnecessarily long and complex replies from AI agents. I created plainspeak to solve this problem. Plainspeak gives your agent a small set of writing rules that run on every reply: plain words, short sentences, direct language, no filler, and no em dashes. Install it once and your agent keeps the voice automatically. Works with Claude Code, Codex, GitHub Copilot, OpenCode, Cursor, Windsurf, Cline, and other agents. Open source. MIT licensed. No API key.
A voice layer for AI agents to write like a human. It bans AI vocabulary and em dashes, and injects plain-voice rules into Claude Code, Codex, opencode, Cursor, and more.
You know the voice. Every reply opens with "Certainly!" or "Let's dive in". Em dashes land in every other line. It says "leverage", "robust", and "seamless" so much you can tell a machine wrote it from across the room. Plainspeak is a voice layer for AI agents. One small set of rules goes into the agent's context and stays there. What should be simple stays simple. Real outputs from the same agent. Left is without plainspeak. Right is with it. I'd start with where the problem actually lives, then narrow it down. The tap in the kitchen/bathroom has a leak that's getting worse — it drips constantly and is starting to waste water. Could you arrange for it to be repaired? The tap in the kitchen…from sufiyan.cc
Does the same job
all alternatives →
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 · 16d 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 · 16d ago · simedw.com