Agentical
AI Agents with Maximal Privacy & Minimal Setup.
What it does
Private, user-owned AI - by design. Prompts, responses, and RAG data never touch our servers. Run state-of-the-art open-source models locally on your own GPU or edge device with a one-click, no-code setup. Encrypted P2P enables things like querying another device’s GPU, multi-agent workflows across machines/users, and compute sharing/delegation. Access control is built in: use an allowlist to decide exactly who can use your AI. Collaboration doesn’t mean giving up privacy.
Does the same job
all alternatives →
- TOTired of duct-taping access control into agent prompts. Here's the fixJun 2026 · github.com · ▲22
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
