Sapa AI
Performance & Security Checks. No Cloud. Free.
What it does
Many people using AI every day are unknowingly wasting tokens, and potentially exposing more data than they realize. We built a macOS app that analyzes, scores, secures, optimizes, and tracks your prompts instantly. We’ve fine-tuned a model specifically for this purpose, optimized for Apple Silicon. It runs entirely on-device and works seamlessly with tools like ChatGPT, Claude, Grok, and more. No cloud. No tracking. Full control. Online and Offline. No browser extensions. And it’s Free.
Does a similar job
all alternatives →
- MWmacOS/Windows AI app that sees, performs actions, and suggests files2023 · mate-os.com · ▲20
Hey Hacker News, my name is Vlad: https://twitter.com/Fortune_VY We’ve been working on IDEs AI assistants for a few years https://www.machinet.net/. Yeah, years :) before chatGPT came along. We have learned a lot about AI models, and how the autoregressive nature coupled with the inability to switch an abstraction level throws a wrench in the works of a possible truly autonomous AI assistant, even OpenAI has featured us on their blog. The more we tinkered with the assistant problem for IDEs, the more we realized the gap between our dream assistant and chatGPT is…
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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 · 27d ago · cactuscompute.com
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app