AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
Local by default. The network when you need more. Peer-to-peer AI inference, bring your own engine, reach the herd. No cloud, no gatekeeper.
Developer toolsRust · JavaScriptGitHub @samtrobertsOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
BitTorrent for LLMs — peer-to-peer distributed inference
Translation pending
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
OpenHydra
Run AI in a herd, not a data center.
A peer-to-peer protocol for free, distributed AI inference.
OpenHydra is a peer-to-peer protocol for distributed AI inference. It does not
run a model itself. Instead it sits in front of whatever inference engine you
already run — Ollama, vLLM, LM Studio, llama.cpp, or any OpenAI-compatible
server — and joins a global swarm that routes each request to a peer that has
the requested model, streams the completion back, and settles a co-signed
receipt. No central server. No API keys. No subscription. Think BitTorrent, for
AI inference.Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
OpenHydra
Run AI in a herd, not a data center.
A peer-to-peer protocol for free, distributed AI inference.
OpenHydra is a peer-to-peer protocol for distributed AI inference. It does not
run a model itself. Instead it sits in front of whatever inference engine you
already run — Ollama, vLLM, LM Studio, llama.cpp, or any OpenAI-compatible
server — and joins a global swarm that routes each request to a peer that has
the requested model, streams the completion back, and settles a co-signed
receipt. No central server. No API keys. No subscription. Think BitTorrent, for
AI inference.Read the full README ↗