Run AI in a herd,
not a data center

Local by default. The network when you need more.

Download the app and run open models on your own machine, free and private. Plug in the engine you already use (Ollama, vLLM, LM Studio, llama.cpp, Exo) and reach a global peer-to-peer network when you need a bigger model. One OpenAI-compatible endpoint. No gatekeeper, no rate limits.

Run today’s AI models right on your own computer, free, private, and no sign-up. When you want something bigger than your machine can handle, OpenHydra quietly borrows a little power from other people’s computers around the world. It works with the AI apps you already use.

Download for your OS
local-first · macOS, Windows & Linux

Prefer the terminal? curl -fsSL https://openhydra.co/install.sh | sh
all downloads & manual install →

Open source No rate limits No account, ever Bring your own engine
Works with your engine
Live now

Cross-continent inference over a direct, hole-punched peer link

A pure-Rust agent, an OpenAI-compatible endpoint, and a libp2p network that punches through CGNAT to connect peers directly, falling back to an encrypted relay when it can’t. Proven between machines on different continents.

Live now

It already works, right across the world

Two computers on different continents are running AI together right now, over a direct, private connection with no company’s servers in the middle. The heart of OpenHydra is real and running today.

🦙

Got a spare GPU, or a Mac that’s always on? Serve the herd while you idle, and earn priority for when you need it back.

Become a provider →

Why OpenHydra

The network for everyone’s local AI

Peer-to-peer inference, BitTorrent, for AI. Bring your own engine, reach the whole herd.

🔌
Plug in what you already run

Ollama, vLLM, LM Studio, llama.cpp, Exo, any engine, any OS, any GPU. A thin Rust agent joins your existing stack to the network. Keep the tools you know; reach the whole herd.

Already use an app like Ollama or LM Studio to run AI on your computer? OpenHydra connects to it and joins it to the network, nothing new to learn.

🦙
Reach models your machine can’t

When you ask for a model you don’t have, the request routes to a peer who already has it loaded, it runs there at full local speed and streams straight back to you.

Want a bigger, smarter AI than your computer can run on its own? Your question is sent to someone whose machine can handle it, and the answer streams straight back to you.

🤝
Free, by reciprocity

Give-to-get: serve inference while you’re idle to earn priority when you consume. Contribute when you can, draw on the herd when you need it.

It’s free, and it stays fair: let others use your computer while you’re not, and use theirs when you need to. Share a little, get a lot.

The five-year-old version

OK but what actually is this?

Glad you asked. It’s honestly not that complicated once you stop calling it “AI infrastructure”.

🌏
Someone already has the model

Somewhere in the herd, the model you want is loaded and running on a real machine right now. The network keeps a live map of who’s serving what.

🌊
Route the question to them

Like BitTorrent finds a peer who has the file, OpenHydra finds a peer who has the model. Your prompt goes there, the answer streams back, no central server in the middle.

🔍
And bad answers get caught

Responses are spot-checked and cross-verified across peers. Good llamas build reputation and get routed more work; cheaters get downranked until the swarm stops trusting them.

Small models run on a single laptop. Bigger ones live on whoever has the hardware. You install once and you’re in, no VRAM math, no “which model fits” anxiety.

How it works

Three steps. Zero guesswork.

Download the desktop app, run an open model locally, and flip a toggle to join the herd when you want more. One switch, zero restart. See how it works under the hood →

01
Download and run, local by default

Install the app for macOS, Windows, or Linux. It runs an open model on your own machine, free, private, offline-capable. No account, no config.

Install the app on Mac, Windows, or Linux. It runs an AI model right on your own computer, free, private, and it even works without internet. No account, nothing to set up.

02
Join the herd when you want more

Flip to network mode to reach bigger models other peers are serving, or reach your own rig at home from anywhere. It’s all behind the same OpenAI-compatible endpoint your tools already speak.

When you want more, flip a switch to reach bigger models running on other people’s computers, or reach your own powerful computer at home from anywhere.

03
Serve while you idle

Leave it running and serve tokens to the herd in the background, that’s how you earn priority, and how the network stays alive. Routing, verification, and encryption are handled for you.

Leave it on and let others use your spare computer power in the background. That’s how you earn priority for later, and it keeps the whole thing running. It all happens automatically.

What you get

Features, listed professionally

We also have proper docs, but here’s the version where we’re allowed to be slightly smug.

⚡
Drop-in OpenAI API
Works with your favourite AI apps

Change one URL and your existing code works. /v1/chat/completions with SSE streaming, plus /v1/embeddings and /v1/models, the OpenAI SDK talks to the whole network unchanged.

If an app can talk to ChatGPT, it can talk to OpenHydra, usually by changing one setting. Your tools keep working, but now they reach the whole network.

🧠
Bring your own engine
Keep the apps you already have

Ollama, vLLM, LM Studio, llama.cpp, Exo, OpenHydra wraps them with a thin adapter. No new runtime to learn, no model re-hosting. Keep the exact stack you already have.

OpenHydra doesn’t replace the apps you use to run AI, it plugs into them. Nothing to reinstall, nothing to relearn.

🔗
Native libp2p networking
Connects computers directly

A Rust libp2p stack: Kademlia DHT discovery across three continents, QUIC + TCP, DCUtR hole-punching, and Circuit Relay v2 fallback. No central broker. If one bootstrap goes down, the llamas find another way.

OpenHydra links people’s computers straight to each other, with no company’s server in the middle. If one connection point goes down, it just finds another way.

🖥
Desktop app for Mac, Windows & Linux
A real app for Mac, Windows & Linux

A Tauri v2 desktop app you can download today: chat with a local model in one click, or flip a toggle to join the global network, no restart, no terminal required.

Download it like any other app. Chat with an AI on your own computer in one click, or flip a switch to reach the wider network, no restart, no typing commands.

🛡
Encrypted, authenticated transport
Private and encrypted

Ed25519 peer identities; every connection encrypted in transit via libp2p Noise and QUIC. Even over a relay the stream stays end-to-end encrypted, the relay just forwards bytes, it never sees your prompt.

Everything you send is scrambled so only the computer answering can read it. Even when your request passes through someone else’s machine, they never see what you asked.

🏅
Reputation & verification built in
Bad answers get caught

Redundant execution and content hashing catch bad actors; reputation decides who gets routed work. Economic security, earned not bought, your standing is the bond.

The network double-checks answers and ranks helpers by how reliable they are. Honest computers get trusted with more work; cheaters get frozen out, your reputation is what keeps everyone honest.

Standing on the shoulders of giants

We didn’t invent this. We just added llamas.

OpenHydra builds directly on two brilliant ideas. We want to be upfront about our inspirations, because intellectual honesty is cool (and mandatory if you don’t want to get ratio’d on HackerNews).

Academic inspiration
Petals

“Run large language models at home, BitTorrent‑style.” Petals proved volunteer compute can serve real LLM inference across the internet. We took that spirit and added a desktop app and a very strong llama motif.

petals.dev →
Protocol inspiration
BitTorrent

Since 2001, BitTorrent has proved you can distribute enormous things to billions of people without a central server, and that reciprocity keeps a network alive. Same energy, applied to tokens instead of files.

bittorrent.com →

🦙 Fun llama fact #1: Real llamas are pack animals because they share the load across the herd. The weakest llama doesn’t carry the whole tent. This is also the core architectural principle of OpenHydra.

🦙 Fun llama fact #2: A group of llamas is called a herd. OpenHydra’s network of peers is also called a herd. We are very consistent in our metaphors and proud of this.

🦙 Fun llama fact #3: The Hydra in Greek mythology had multiple heads, cut one off and two grow back. Our bootstrap nodes work the same way. (Please don’t cut our bootstrap nodes.)

🦙 Fun llama fact #4: Llamas can spit up to 10 feet when stressed. Our nodes politely return HTTP 503 instead. Both are valid responses to being overwhelmed.

Join the herd

Everything’s better with company.

Ask questions, show off your rig, and help shape where OpenHydra goes next. It’s open source, the community is small and friendly, and yes, aggressively llama-themed.

Join the Discord Star on GitHub

Your laptop is a supercomputer waiting to happen.

It’s sitting there doing nothing useful right now. Download the app and it runs AI locally in one click, then joins a global herd of volunteers when you need more. No cloud. No lock-in. Just llamas.

Download for your OS