Pinned Loading

1. arle arle Public

   Pure-Rust LLM runtime: one binary serves (OpenAI-compatible), runs local agents, and distills models on their own rollouts — on Apple Silicon and NVIDIA. No Python on the hot path.

   Rust 20

2. eli eli Public

   Ease Lives Instantly

   Rust 5

3. dsx dsx Public

   Forked from openai/codex

   Lightweight deepseek coding agent that runs in your desktop

   Rust 2

4. kernel-set kernel-set Public

   High-performance CUDA kernels for LLM inference & training — callable from Python, Rust, Go, and TypeScript through one stable C ABI.

   Python 2

5. ckl-bench ckl-bench Public

   ckl's personal benchmark for doc writing, infra code, and paper reading — one-click evaluation of the latest models via TUI coding CLIs with an interactive dashboard.

   HTML 1

6. lessons lessons Public

   Python