A2A protocol for Elixir with GenServer-like ergonomics
Hello! I wanted A2A support for an Elixir project and thought about how I wanted to use it in my app, and less about the protocol. This became a GenServer-like protocol for an agent. The package has basic support and complies to the A2A TCK suite. Most of the project is LLM-coded, but with detailed planning and review at each step. Less than a week from initial idea to first hex.pm release - all coded on the side of other work. Interesting times where such a thing is possible. Just after publishing I did find an existing Elixir package implementing A2A (not sure how I could miss it at…
What it does
In the maker’s words, at launch
Hello! I wanted A2A support for an Elixir project and thought about how I wanted to use it in my app, and less about the protocol. This became a GenServer-like protocol for an agent. The package has basic support and complies to the A2A TCK suite. Most of the project is LLM-coded, but with detailed planning and review at each step. Less than a week from initial idea to first hex.pm release - all coded on the side of other work. Interesting times where such a thing is possible. Just after publishing I did find an existing Elixir package implementing A2A (not sure how I could miss it at first). The other package has different semantics and was different enough for me to decide to keep mine up. In any case, feedback and comments are welcome as always! Thanks, Max
Does the same job
all alternatives →
- SCSmart contract decompiler that uses symbolic execution2018 · ▲68
Hi All, I released an EVM/Solidity decompiler recently, here: http://www.eveem.org/ Since it uses symbolic execution underneath, the results are quite awesome. There is also an api that delivers a .json / middle language representation of every contract here: http://eveem.org/code/{{address}}.json The plan is to open-source it as soon as I clean up the code a bit. Spent the last two month crunch-time to get it delivered from scratch :)
- AAAwesome-A2A – curated resources for Google's Agent2Agent protocol2025 · github.com · ▲5
Open-source list of libraries, demos, and tools for Google’s new Agent2Agent (A2A) protocol. Docs in EN/中文/JA/ES/DE/FR. Looking for feedback & PRs!
- TETopical – Elixir library for synchronising state to web clients2023 · github.com · ▲8
Hi HN. I've been working on an Elixir library for synchronising state, maintained by the server, to connected web clients. I found this was something I kept implementing for side-projects, so I've extracted it into a library. It solves a similar problem to Phoenix LiveView, but aimed at a different level of abstraction: rather than synchronising HTML and UI events, this just synchronises (JSON-serialisable) state. Topics can be shared between connected users, and each client can subscribe to multiple topics. The library takes care of starting topic instances (GenServer processes) as needed,…
- OAOpenRig – agent harness that runs Claude Code and Codex as one systemApr 2026 · github.com · ▲8
I've been running Claude Code and Codex together every day. At some point I figured out you can use tmux to let them talk to each other, so I started doing that. Once they could coordinate, I kept adding more agents. Before long I had a whole team working together. But any time I rebooted my machine, the whole thing was gone. Not just the tabs. The way they were wired up, what each one was doing, all of it. Nothing I'd found treats your agent setup as a topology, as something with a shape you can save and bring back. So I built OpenRig, a multi-agent harness. A harness wraps a model. A "rig"…
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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
