Jade – an iMessage blue bubble agent for group chats
I thought it’d be fun to create an agent that lives in iMessage, and most of all that works in group chats on iMessage. I called her Jade Multiplayer experiences with agents haven’t been really explored as much, and it was interesting to test the boundaries of LLMs with respect to that. I used durable objects from Cloudflare for the backend, and a MacMini that’s always online to handle the reading and writing to iMessage. The nice part is that it decides whether to reply in the group chat, a bit like a human would. It doesn’t always reply like you’d expect in a ChatGPT-like setting. And it…
What it does
In the maker’s words, at launch
I thought it’d be fun to create an agent that lives in iMessage, and most of all that works in group chats on iMessage. I called her Jade Multiplayer experiences with agents haven’t been really explored as much, and it was interesting to test the boundaries of LLMs with respect to that. I used durable objects from Cloudflare for the backend, and a MacMini that’s always online to handle the reading and writing to iMessage. The nice part is that it decides whether to reply in the group chat, a bit like a human would. It doesn’t always reply like you’d expect in a ChatGPT-like setting. And it can also understand images! It was a fun project to work on, I may write a detailed technical post about it if there’s interest. See a demo here: https://x.com/albtaiuti/status/1899445452145373201
Does the same job
all alternatives →
- AMAMA2, messenger built for AI agentJun 2026 · ama2.me · ▲5
I'm a solo founder building AMA2, a messaging runtime made for AI agents. This is my first Show HN, so I'd really appreciate your feedback. What brought me this idea: At first, I was building an AI agent for solo creators that knows everything about you and can do business chore on your behalf. When I tried to plug it into normal chat tools like Telegram, Discord, Slack... , they all felt wrong for agents: 1. They don't care about an agent's context. To follow a thread, the agent has to pull the whole history every time. 2. Giving each agent its own account is painful. If you have (or will…
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, March 2025
the whole month →
Mimic Human Research & Save Findings in AI Knowledge Base
AI · 2025 · sider.ai
