3-day current streak·5-day longest streak
-
hermes-optimization-guide ★ PINNED
Hermes Agent setup, migration, LightRAG, Telegram, and skill creation guide
Shell ★ 458 2d agoExplain → -
openclaw-optimization-guide ★ PINNED
Make your OpenClaw AI agent faster, smarter, and cheaper. Speed optimization, memory architecture, context management, model selection, and one-shot development guide.
JavaScript ★ 352 23h agoExplain → -
prompt-cache-skills ★ PINNED
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.
Python ★ 104 22d agoExplain → -
turboquant ★ PINNED
First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.
Python ★ 71 25d agoExplain → -
UltraCode-Shim ★ PINNED
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.
Python ★ 355 1d agoExplain → -
windsurf-unlocked
Every feature Cascade ships that most people aren't using — configured properly
Python ★ 44 1mo agoExplain → -
kvtc
First open-source KVTC implementation (NVIDIA, ICLR 2026) -- 8-32x KV cache compression via PCA + adaptive quantization + entropy coding
Python ★ 19 2mo agoExplain → -
Hermes-caduceus
Caduceus — Hermes-native UltraCode dynamic-workflow mode (Dynamic Workflows)
Python ★ 16 14d agoExplain → -
DevinCLI-Unlocked
Unlock the true power of DevinCLI with all the of the resources I have gathered for you
★ 15 17d agoExplain → -
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.
PowerShell ★ 12 17d agoExplain → -
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.
Python ★ 10 8d agoExplain → -
oh-my-mythos
A stateful reasoning runtime for OMP coding agents. Evidence ledger, obligation tracking, verification gates, and identity-aware retry blocking.
JavaScript ★ 0 3d agoExplain → -
gpuview
GPU-native screen vision for AI agents — DXGI Desktop Duplication capture + compositor dirty-rect change feed. 96% less image data than full-frame screenshots.
C# ★ 0 9d agoExplain →
No repos match these filters.