A elegantly enhanced Telegram Bot which can download torrents, mega, google drive links, telegram file, direct links and all yt-dlp sites, upload to google drive, telegram cloud, rclone clouds or ddl servers. Made with wzgram in Python by WZML-X Devs.
- aria2c
- bot
- clone
- download
DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks
DSH Plugin Radar — open-source ecosystem radar for DeepSeek Harness plugins: continuous discovery (21k+ candidates), k8s runtime validation (13k+ tests), 15-min snapshots; the catalog is a generated artifact — 开源 DSH 插件生态雷达:持续发现 2.1 万+ 候选、k8s 运行级实测 1.3 万+、15 分钟快照;插件目录为自动生成的产物
Expert Parallelism Load Balancer
The repository host gives no description.
[NeurIPS 2025] 🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability
Repo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)
- diffusion-transformer
- image-restoration
- one-step-diffusion-model
- video-restoration
Open source, privacy-first Voice of Customer analytics. A self-hosted alternative to Enterpret and Unwrap that strips PII from feedback before any LLM sees it.
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
An IDA plugin for binary file analysis, powered by AI models such as OpenAI and DeepSeek.
- binary-analysis
- chatgpt
- ida
- ida-plugin
一句话生成大师级海报、书籍封面、专辑封面和各类设计作品。无需懂PS、配色或艺术史,AI自动选择最佳风格(基于20位传奇海报设计师)。支持电影海报、读书笔记、公众号封面、小红书配图等。默认9:16竖版,完美适配社交媒体。包含AI提示词优化、风格对比、图生图转换功能。触发词:"Mondo风格"、"书籍封
Effortlessly request recommended movies, TV shows and anime to Jellyseer/Overseer based on your recently watched content on Jellyfin, Plex or Emby—let SuggestArr handle it all automatically, keeping your library fresh with new and exciting content!
DeepSeek Harness (DSH) ecosystem: curated plugins, tools, and infrastructure from dsh-external/hub and the public dsh-plugin topic.
Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
AI-powered tool for efficient abstract and PDF screening in systematic reviews.
Use an air-gapped Raspberry Pi Zero to sign for Bitcoin transactions! (and do other cool stuff)
基于Yolov5车牌检测,更快更准.
为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!
Build your own Raster dynamic map tile services
A generalized information-seeking agent system with Large Language Models (LLMs).
Standalone application to aggregate data from the Plex ecosystem into InfluxDB using Grafana as a frontend
Local-first AI video recasting with draft review, explicit HD approval, and source-audio restoration.