SIPA OS
AI≠EFECTIV;AI=PRACTICE;+WEB SHELL;buy architec for neuro
What it does
SIPA OS is a self-hosted AI infrastructure layer for creative entrepreneurs. Built by a UV artist with ADHD who needed a system that doesn't break or hallucinate. Features: • Multi-node AI stack (8 agents) • Unified webhook hub (Zendesk, Intercom, Slack, Airtable) • Forensic file system with SHA256 on every artifact • Zero-UI philosophy for neurodivergent operators • 100% self-hostable, no vendor lock-in. It maintains state so you can focus on creating. Truly executes.
Does the same job
all alternatives →
Embedded iPaaS from Albato2025 · albato.com · ▲657Make your SaaS stick with AI-fueled embedded iPaaS
- IPI put an AI agent on a $7/month VPS with IRC as its transport layerMar 2026 · georgelarson.me · ▲340
The stack: two agents on separate boxes. The public one (nullclaw) is a 678 KB Zig binary using ~1 MB RAM, connected to an Ergo IRC server. Visitors talk to it via a gamja web client embedded in my site. The private one (ironclaw) handles email and scheduling, reachable only over Tailscale via Google's A2A protocol. Tiered inference: Haiku 4.5 for conversation (sub-second, cheap), Sonnet 4.6 for tool use (only when needed). Hard cap at $2/day. A2A passthrough: the private-side agent borrows the gateway's own inference pipeline, so there's one API key and one billing relationship…
- VAVoxos.ai – An Open-Source Desktop Voice Assistant2024 · gitlab.com · ▲123
Voxos is an open-source desktop voice assistant that aims to put Clippy to shame while supporting new desktop workflows powered by LLMs. Tired of copy and pasting ChatGPT responses between your web browser and IDE? Does your copilot not quite do what you need it to do? I invite you to give Voxos a try and maybe even become a contributor!
- IBI built a 1.8MB native app with self-built UI, vision and AI librariesDec 2025 · github.com · ▲15
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