TerpBot
@OnlyTerpI fix things for people. Everyday I get better at fixing things. I do it for the thrill of solving a problem.
Language Breakdown
Lines of code distribution across 12 owned repositories
I-Shaped Developer
I-shapedSpecialist — deep expertise in Python
Collaboration Network
Global Impact visualization
Repos
13
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
Top Repositories
Hermes Agent setup, migration, LightRAG, Telegram, and skill creation guide
Make your OpenClaw AI agent faster, smarter, and cheaper. Speed optimization, memory architecture, context management, model selection, and one-shot development guide.
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.
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.
First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.
Every feature Cascade ships that most people aren't using — configured properly
First open-source KVTC implementation (NVIDIA, ICLR 2026) -- 8-32x KV cache compression via PCA + adaptive quantization + entropy coding
Caduceus — Hermes-native UltraCode dynamic-workflow mode (Dynamic Workflows)
Unlock the true power of DevinCLI with all the of the resources I have gathered for you
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.
Open Source Impact
Contributions to external projects
