Settings

Theme

Show HN: Rebuilt SETI Home but for AI

github.com

4 points by s4saif 16 days ago · 4 comments · 1 min read

Reader

It’s a single Go binary that turns unused home GPUs into a decentralized, peer-to-peer AI compute grid. Think SETI@home, but for running local LLMs and AI workloads.

ajkhn 16 days ago

SETI@home looked for intelligent life in space. AgentFM looks for spare VRAM on my home network. Honestly, not sure which one is harder to find .....

yennim 16 days ago

Interesting, btw how would you establish the trust from the untrusted notes?

s4saifOP 16 days ago

The Problem: Cloud compute for heavy AI inference is expensive, yet millions of consumer GPUs sit totally idle most of the day. What it does: AgentFM is a single Go binary that pools those idle machines into a decentralized grid. It lets you offload heavy AI workloads from a weak machine to capable GPUs across the network without relying on central servers.

To make this work without a centralized broker, it’s built on go-libp2p using two main algorithms:

Routing & Discovery: It uses Kademlia DHT to find peers and handle NAT hole-punching, letting standard home internet connections talk directly.

State & Telemetry: It uses a GossipSub protocol where nodes broadcast their real-time hardware capacity (VRAM/CPU load). This ensures the network dynamically routes heavy tasks to capable hardware and avoids sending jobs to nodes that would instantly OOM crash.

I'm still iterating on the sandboxing for untrusted nodes, but I would love to hear what you guys think of the networking architecture!

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection