Pinned Loading

1. roadrunner-inference roadrunner-inference Public

   A novel architecture for accelerating transformer inference without retraining, using SVD-based adaptive routing and dot product prediction. Near 100% accuracy, all without any model weight modific…

   Python 1

2. in_network_matmul_and_llm_inference in_network_matmul_and_llm_inference Public

   Python

3. nexal nexal Public

   A language designed for maximum token efficiency and AI-native communication

   Python

4. otto_agent otto_agent Public

   Otto - Python Cursor-like Agent

   Python

5. vessel_sdk vessel_sdk Public

   Official SDK for the Vessel Platform: `https://vessel-platform.acampi.dev`

   Python