Nick

graymatter. Three lines of code to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.

coffeegraph. One folder. One command. Your complete AI agency running on autopilot while you drink coffee. ☕

epica. Embeddable Rust runtime for formal AGM belief revision in LLM agents — dual-process uncertainty quantification, C=(P,I,G,R) behavioral contracts, 9 Mnemonic Sovereignty primitives, MCP 2026 native, PyO3 SDK.

Stratum. Adaptive dual-tier serving for Gemma 4 on consumer 16GB GPUs. Complexity + real-time VRAM routing between vLLM E4B and llama.cpp 27B. Production stack with OpenWebUI, monitoring, and more.