TerpBot

hermes-optimization-guide. Hermes Agent setup, migration, LightRAG, Telegram, and skill creation guide

UltraCode-Shim. Give Claude Code's ultracode mode to ANY model you already pay for. A tiny local proxy + one config.json. Point your AI at AGENTS.md and it sets itself up.

openclaw-optimization-guide. Make your OpenClaw AI agent faster, smarter, and cheaper. Speed optimization, memory architecture, context management, model selection, and one-shot development guide.

prompt-cache-skills. Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.

turboquant. First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.

windsurf-unlocked. Every feature Cascade ships that most people aren't using — configured properly

kvtc. First open-source KVTC implementation (NVIDIA, ICLR 2026) -- 8-32x KV cache compression via PCA + adaptive quantization + entropy coding

Hermes-caduceus. Caduceus — Hermes-native UltraCode dynamic-workflow mode (Dynamic Workflows)

DevinCLI-Unlocked. Unlock the true power of DevinCLI with all the of the resources I have gathered for you

windows-is-fine-for-llms. The old advice to avoid Windows for local LLMs used to be right. It isn't anymore. The fixes for display-GPU desktop crashes and WSL memory limits, from people who run a 5090 daily.

nemotron-opus-elicitation. 29 controlled experiments on Nemotron 3 Ultra: what prompting can and cannot do to a frontier model. Voice 4/8 to 7/8, hidden bugs 1/5 to 5/5 — blind dual-judge graded, no fine-tuning.