Lists (3)
Starred repositories
为 DeepSeek Harness (DSH) 插件生态打造的现代化桌面端解决方案。万物皆「插件」，桌面本身也是「插件」。
DeepSeek Harness: Everything is a Plugin.
DeepSeek Harness（DSH）Web 插件聚合生态包 · 一切皆插件，创意工坊分发
AI 短剧制作的 skill 集合：拆角色、排大纲、出场景与道具设定、写剧本、切分镜 | Agent skills for AI short-drama production — character bibles, adaptation outlines, art bibles, screenplays, storyboards. Runs in Claude Code & codex.
A curated list of plugins for DeepSeek Harness (dsh) · DeepSeek Harness 插件精选列表
把 DeepSeek Harness 装进你的口袋：电脑上跑 dsh web，手机扫码即同步访问（局域网 + 公网，实时同屏）Put DeepSeek Harness in your pocket: run dsh web on your computer and access it synchronously by scanning a QR code on your phone (LAN…
J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace research. | 哔哩哔哩：Tiger380 (UID 3494375382321675) — https://space.bilibili.com/3494375382…
专注于绚丽的歌词动画效果的本地音乐/navidrome/第三方多平台在线音乐播放器
Single-container self-hostable Readest fork — SQLite + local FS, no Supabase, no paywall. Community: https://nodebyte.cn
Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.
Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
Custom node to load models in INT8 for 1.5~2X Speed gains on 30 series cards.
Jean-Pierre Serre《Lectures on the Mordell-Weil Theorem》中文翻译
Run Docker images on Android Termux without Docker engine.
🤖 A minimal and customizable Docker image running the Android emulator as a service.
Host Home Assistant Docker Container in Android Device.
Run Docker images in Termux via Udocker. No root, no qemu-VM, much faster.
AdaLLM is an NVFP4-first inference runtime for Ada Lovelace (RTX 4090) with FP8 KV cache and custom decode kernels. This repo targets NVFP4 weights and keeps the entire decode path in FP8
让你在 ComfyUI 中快捷的使用提示词工具 quickly use the prompt word tool in ComfyUI
🏛️面向人文社科研究的 OCR 利器：多引擎驱动，高精度识别，任意设备可跑，开箱即用，繁体竖排支持，输出双层 PDF / 带页码 TXT。
TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC