Bloks
AI agents that live on your Mac, not in someone's cloud
What it does
Most AI agent tools run in someone else's datacentre with your mail and files wired into it. Bloks runs on your Mac instead. Agents get names, roles and seniority. Put a few in a room and the most senior one runs the meeting. They answer with charts and checklists rather than walls of text, and they stop to ask before they send, spend or delete anything. It uses the Claude or Codex subscription you already pay for. No account, and nothing leaves your machine. Free and open source.
Agents as contacts, rooms as group chats. Bloks is a local-first workspace for personal AI agents. Free forever with your own keys.
Not to a company. Not to a subscription. To you, on the machine in front of you. Free forever. No account. The iPhone app is in review with Apple. Your work. Your habits. Your half‑finished thoughts. All of it a guest in someone else's building. They set the rent. They read the mail. They can ask you to leave. Bloks runs entirely on your Mac. Your agents, your conversations and your keys sit in ~/.bloks on your disk. There is no Bloks account, because there is no Bloks server to hold one . The only thing that leaves this machine is the engine you picked, talking to the provider you already pay. Bloks is not in the middle. Bloks never asks who you are. No sign-up, no email, nothing to…from bloks.dev
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 · 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 · 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 · 17d ago · simedw.com