Pinned Loading

1. voxelnav voxelnav Public

   Real-time semantic voxel mapping for ROS2 robots - 100ms latency on Jetson Nano

   C++ 19 1

2. kvquant kvquant Public

   Drop-in KV cache compressor for local LLM inference - Run 70B models on 8GB RAM

   Python 6

3. GhostPilot GhostPilot Public

   GPS-Denied Drone Navigation with Agentic AI - VINS-Mono + Nav2 + LLM Mission Parser

   Python 1

4. SignalHop SignalHop Public

   HTML 1

5. kernelweave kernelweave Public

   KernelWeave: self-compiling skill kernels for LLMs

   Python 1

6. middleout-lattice middleout-lattice Public

   Neural compression for model files and data - beats bz2 on text/code

   Python 1