obscura

The headless browser for AI agents and web scraping

wikiwise

暂无简介

svg-hand-drawn-skill

暂无简介

ddtree

暂无简介

claude-code-memory-setup

Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. 🇧🇷 PT-BR included.

llm-production-toolkit

Production-ready toolkit for evaluating, monitoring, and ensuring safety of LLM deployments. Hallucination detection, bias evaluation, feedback loops, and production readiness assessment.

agora

31 位思想家组成的多 Agent 审议系统，覆盖工程、商业、人生抉择、关系、心理、创作六大领域。黑格尔正反合结构，一个命令开启深度辩证。

nanoPD

nanoPD A from-scratch Prefill/Decode disaggregation inference engine for LLMs --- Disaggregated inference separates the two phases of LLM generation — the compute-intensive **prefill** processing the prompt and the memory-bandwidth-bound **decode** generating tokens one a

flow-llm-router

The Ultimate "Token Saver"

GHFS

Mount GitHub repositories as a virtual read-only macOS filesystem

wiki-os

UI Layer for Karpathy's LLM Wiki

hermes-web-ui

Hermes Web UI Web dashboard for Hermes Agenthttps://github.com/NousResearch/hermes-agent — chat interaction, session management, scheduled jobs, usage statistics, platform channel configuration, and log viewing. Tech Stack - **Vue 3** — Composition API + `` - **TypeScript** - **Vite** — Build t