3 projects
turborag
Compressed vector and graph-augmented retrieval engine with adaptive two-stage search, implementing TurboQuant/QJL quantization from Google Research.
gearbx
Entropy-Routed Dynamic Quantization for LLM Inference
amcl-server
A/MCL — Agent/Multi-Coding-agent Context Layer. MCP server for automatic context persistence across AI coding agents.
