Trama
Create macOS native automations using plain language
What it does
Zapier and Shortcuts make you think like a programmer: blocks, flows, conditions. Trama removes that layer. Press Cmd+Option+X, describe what you repeat in your own words, and it runs in the background. What is different: · Your language, not just English · Native Mac reach: AppleScript, shell, OCR, screen awareness · It notices what you repeat and suggests the automation · If it breaks, AI explains the error and fixes it in one tap · Your key: Claude, GPT, Gemini, Groq.
Trama hears what you repeat and quietly builds the automation. macOS app — no code, no diagrams, just plain English.
No code. No diagrams. Describe what you do every day — Trama builds it and runs it by itself. macOS 15.7 (Sequoia) or later · Apple Silicon and Intel · No credit card Connect once in the Integrations panel. No API key hunting, no webhook setup. Every plan uses your own AI key (Anthropic, OpenAI, or Google) — unlimited runs, and you pay your provider directly only for what you use. Trama is rolling out to a small group first. Tell us about yourself and we'll reach out when your spot isfrom usetrama.com
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