Prime
Native, lightweight for AI agents. Rust & Tauri v2
What it does
Prime is a native, ultra-lightweight (5MB) desktop OS engineered for autonomous AI agents. Built with Rust and Tauri v2, it eliminates the heavy resource footprint of Electron-based tools. It features a unique 7-tier Cognitive Memory architecture, built-in support for 12+ MCP servers, an advanced Stealth Browser for computer use, and strict capability-based security. Ready for local execution with Ollama or cloud models, offering an immersive glassmorphic interface with full RTL/Arabic support.
Does the same job
all alternatives →
- WMWe made our own inference engine for Apple Silicon2025 · github.com · ▲186
We wrote our inference engine on Rust, it is faster than llama cpp in all of the use cases. Your feedback is very welcomed. Written from scratch with idea that you can add support of any kernel and platform.
- HOHART OS – an open-source AI OS built so frontier AI needs no datacenterJul 2026 · github.com · ▲18
- AAAnything AI – A local Zapier (like) AI tool written in Rust2024 · github.com · ▲7
Hey HN! I really like local apps for their simplicity and privacy and hate paying Saas bills and I wanted a way to start automating my life with AI so I started building Anything. Anything is built on Tauri so the front end is React and the "backend" is Rust. It's 100% local & 100% doesn't ask you to spin up docker to use. Another core goal of the app is to get away from "package bloat" you see in other general purpose AI oss projects where they have a package.json that is 300 lines long ( more on that later. ) Oh btw I suck at Rust! I learned Rust while building this so the code is _not…
Shadow-OSMay 2026 · shadow-os-ai.vercel.app · ▲4Autonomous AI agent that automates tasks in the shadows.
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 · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com