Hey HN,
I was building a multi-agent swarm and realized I was burning 90% of my latency and credits just having Agent A turn its math into English (JSON) so Agent B could turn it back into math. It felt like two supercomputers communicating via smoke signals.
I thought, "Why not just send the hidden state?"
I accidentally fell down a rabbit hole and built Nexus Protocol (open source). It’s a Python library that bridges the latent spaces of different models (e.g., Llama-3 to Mistral).
How it works:
Extracts the latent vector from the sender (skipping the decoding head).
Passes it through a lightweight linear adapter (trained on semantic pairs) to align dimensions/spaces.
Injects the result directly into the receiver's context embedding layer.
The result: "Telepathy." The receiver "understands" the concept and acts on it without a single token being generated or read. It runs on consumer hardware using bitsandbytes 4-bit loading.
It’s still early (proof-of-concept level), but the speedup is massive. I’d love for you guys to roast my implementation or tell me why this is a terrible idea.
pip install nexus-protocol
I'd also give a shout out to AmiKit.[0] It's pretty slick, and has a ton of software already setup. You still need to get the Kickstart ROMs from AmigaForever. The only thing is it's different from vanilla Amiga workbench.
Yep was going to say for example PiMiga is an awesome project, and the maintainer puts his heart and soul and loads of time into it. Believe it works on amd64 now too (not just pi/arm).
