Pinned Loading

1. gadak gadak Public

   Your Jira and Confluence, mirrored into one local SQLite file — macOS app, web UI, and agent SQL/MCP. Instant search, offline, one binary.

   Go 43 5

2. rig-log rig-log Public

   A build log for one workstation: a 284B mixture-of-experts model across two GPUs and 256 GB of RAM, measured.

   Python 1

3. bloomery bloomery Public

   Hybrid GPU + CPU inference for mixture-of-experts models, written in Rust down to the CUDA kernels. A drop-in llama-server.

   Rust 15 1

4. toktape toktape Public

   The black-box tape for local LLM serving: attach to a running llama-server, record one run, and get a card that settles the argument.

   Go 2