Back to directory

Hypha

A generative-AI-powered application framework for large-scale data management and AI model serving, connecting compute services across distributed locations through virtual workspaces and remote procedure calls.

Hypha

Hypha is a framework for building platforms that combine data management, AI model serving and real-time communication. Clients connect to virtual workspaces, similar in concept to video-call rooms, where they can call other connected services as if the calls were local functions, using Hypha's bidirectional RPC layer, Hypha-RPC.

Developers can integrate compute services such as AI models and data-analytics tools into these workspaces, and large language models can then orchestrate the connected services to build automation platforms and agentic workflows. Target use cases include research-institution data platforms, autonomous agent systems and distributed data services.

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.