Back to directory

Diffuse

A peer-to-peer network of ordinary machines that runs large language models across the network so a prompt is served without a central operator, encrypted so it never leaves the sender's device in clear text.

Visit website (opens in a new tab)diffuse-systems.github.io
Diffuse

Diffuse runs large language models across a peer-to-peer network of ordinary computers rather than on a company's own servers. Prompts stay encrypted end to end so no single operator can read them, and the project positions itself for people who do not want their queries logged or surveilled by a central provider.

It installs as a single prebuilt binary for Linux, macOS and Windows with a companion Python worker, requiring no account, API key or server of your own; unsupported platforms can build it from source with Cargo. The network's infrastructure is run by the people participating in it rather than by a company.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.