OPEN SOURCE · DISTRIBUTED AI

Stronger AI.
Built together.

ShardAi pools idle RAM and VRAM across multiple devices, shards large language models, and runs inference over a peer-to-peer network.

Open source · Tauri desktop client · Python inference engine

P2PPeer-to-peer connections
LLMDistributed model inference
RAM + VRAMShared computing resources
OPENOpen source on GitHub
01 / TECHNOLOGY

No supercomputer required.

ShardAi distributes model workloads across the devices you already have, bringing them together in a collaborative AI inference pipeline.

01

Flexible model sharding

Assign GGUF model layers based on the RAM and VRAM limits you choose, so multiple devices can contribute within their available capacity.

↗

Hybrid P2P networking

Discover devices on your local network with mDNS/UDP, or connect over the internet through a signaling tracker.

⌘

A lightweight desktop app

The Tauri desktop app combines React and Rust, while the Python core engine uses llama.cpp for inference and sharding.

⇣

Download only what you need

Automatically download and cache the weights for assigned model layers, directly from Hugging Face.

◎

Tensor pipeline

Nodes pass serialized, compressed tensors along the pipeline, processing the model one stage at a time.

⌕

Built to be inspected

ShardAi is MIT-licensed open-source software. Explore the architecture, follow progress, and contribute on GitHub.

02 / HOW IT WORKS

From individual devices to collaborative AI.

Each node contributes its available computing resources. Together, the nodes form a distributed inference pipeline.

STEP 01 — CONNECT

Discover peers

Devices register their available resources with a signaling tracker and find other peers on the network.

STEP 02 — ALLOCATE

Load model layers

The engine downloads the required weights, then loads the layers assigned to each device.

STEP 03 — INFER

Run the pipeline

Each peer computes its part and passes tensors to the next node in the sequence.

START EXPLORING

The AI network starts with you.

Discover the technology, follow the roadmap, and help build ShardAi in the open.