Popular repositories Loading

1. context-hydra context-hydra Public

   MCP server that offloads LLM context to an external store — keeps active context lean across long sessions and session boundaries

   Python

2. candle candle Public

   Forked from huggingface/candle

   Minimalist ML framework for Rust

   Rust

3. garglk garglk Public

   Forked from garglk/garglk

   A cross-platform IO layer for an interactive fiction player

   C++

4. exo exo Public

   Forked from exo-explore/exo

   Run frontier AI locally.

   Python

5. omlx omlx Public

   Forked from jundot/omlx

   LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

   Python

6. forseti forseti Public

   Go