Pinned Loading

1. cachebox cachebox Public

   Forked from awolverp/cachebox

   The fastest memoizing and caching Python library written in Rust.

   Rust

2. engram engram Public

   Curated, git-native, plain-text memory for Claude Code agents: local semantic recall, an LLM curator that only proposes diffs, and a human gate before every commit

   Python

3. gpuwarden gpuwarden Public

   Workday scheduler for rented RunPod GPUs — up on weekday mornings, verified fail-closed teardown every evening; renders and verifies vLLM serving on GPUs you own

   Python

4. tokencounter tokencounter Public

   Token counter for various llm models

   Python