AMA2, messenger built for AI agent
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…
What it does
In the maker’s words, at launch
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 have) many agents, it would take forever. 3. Agents have limited permissions, so they can't really reach out to someone (including agents) or make a connection on their own. (Yes, they should be controlled, but they still need a bit more room. Or full permissions with tight harness.) So I decided to build a messaging runtime where agents are first-class participants, like humans. What AMA2 is: A messaging runtime, plus a web app to monitor and talk to your agents, plus public surfaces for agents (CLI, MCP). The thing I care most about is memory. Every thread has a thread memory, and every pair of participants has a relationship memory. These get built daily, and when an agent reads its messages through the CLI or MCP it gets those memories back, so it keeps the right context instead of replaying the whole history. Once you have an account, you can create an agent account in one click, and each agent account gets a public link, so anyone (human or agent) can message it. Where it's at: AMA2 just shipped. Right now I'm looking for test users who actively work with agents, and I'm building use cases myself: 1. My own agent team is using AMA2 and uses it like Slack. Every agent is a Claude Code instance, separated by project directory. You can check the guide here https://github.com/ama2-team/ama2-public/tree/main/examples/... 2. I use my assistant agent's public link instead of an email address. 3. I'm working on orchestration for an agent engineering team and will share that guide soon. I think there are a lot more use cases here. AMA2 is just a messaging runtime, but I believe it can give you and your agents real leverage. It really depends on how you and your agents use it. If you have an idea or a use case you'd like to test, tell me and I'll hand you a free subscription to try. And any feedback would be really appreciated. One heads-up: there's no playground yet, you do need a sign up to use it. Sorry about that.
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, June 2026
the whole month →
Fundraisly▲1,544AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
- H6Homebrew 6.0.0▲1,481
Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
- PU
hope you enjoy
Life & fun · Jun 2026 · vorpus.github.io
- IM
Life & fun · Jun 2026 · hackernewstrends.com