(NOW ONLY FOR NFTABLES) Port zapret-discord-youtube from Flowseal and bol-van for easy to use on linux!!! Внимание, это stable4 ветка. !!! На ней я захардкодил последний рабочий конфиг от Flowseal на коммите 8a1885d7d06a098989c450bb851a9508d977725d. Соотвественнно новые стратегии пока не подтягиваются. Включать автообновление пока не имеет смысла, так как захардкожена эта версия. Сам доберусь до апдейтов вероятно не скоро. Также можете попробовать эту версию от Snowy-Fluffy Что это? Это адаптер…
🐹 Deep clean and optimize your Mac. Mole Deep clean and optimize your Mac. Features Unified toolkit: Consolidated features of CleanMyMac, AppCleaner, DaisyDisk, and iStat into a single binary Deep cleaning: Scans and removes caches, logs, and browser leftovers to reclaim gigabytes of space Smart uninstaller: Thoroughly removes apps along with launch agents, preferences, and hidden remnants Disk insights: Visualizes usage, manages large files, rebuilds caches, and …
Expose your local web server to the internet with a public URL. tunnelto tunnelto lets you expose your locally running web server via a public URL. Written in Rust. Built completely with async-io on top of tokio. Install Usage Instructions Host it yourself Install Brew (macOS) brew install agrinman/tap/tunnelto Cargo cargo install tunnelto Everywhere Or Download a release for your target OS here: tunnelto/releases Usage Quick Start tunnelto --port 8000 The above command o…
A native desktop charting platform for crypto marketsFlowsurface An experimental open-source desktop charting application. Supports Binance, Bybit, Hyperliquid and OKX Key Features Multiple chart/panel types: Heatmap (Historical DOM): Uses live trades and L2 orderbook to create a time-series heatmap chart. Supports customizable price grouping, different time aggregations, fixed or visible range volume profiles. Candlestick: Traditional kline chart supporting both time-based and cust…
Light Video Generation Inference Framework ⚡️ LightX2V: Light Video Generation Inference Framework [ English | 中文 ] LightX2V is an advanced lightweight video generation inference framework engineered to deliver efficient, high-performance video synthesis solutions. This unified platform integrates multiple state-of-the-art video generation techniques, supporting diverse generation tasks including text-to-video (T2V) and image-to-video (I2V). X2V represents the transformation of diffe…
Reference PyTorch implementation and models for DINOv3🆕 [2025-09-17] 🔥 DINOv3 backbones are now supported by the PyTorch Image Models / timm library starting with version 1.0.20 [2025-08-29] DINOv3 backbones are supported by released versions of the Hugging Face Transformers library starting with version 4.56.0 [2025-08-14] DINOv3 backbones are now available in Hugging Face Hub and supported by the development version of the Hugging Face Transformers library DINOv3 🦖🦖🦖 Meta AI Research, FAIR Or…
AI-Powered Dark Web OSINT Tool Robin: AI-Powered Dark Web OSINT Tool Robin is an AI-powered tool for conducting dark web OSINT investigations. It leverages LLMs to refine queries, filter search results from dark web search engines, and provide an investigation summary. Installation • Usage • Contributing • Acknowledgements Features ⚙️ Modular Architecture – Clean separation between search, scrape, and LLM workflows. 🤖 Multi-Model Support – Easily switch between OpenAI, …
A framework for efficient model inference with omni-modality models Easy, fast, and cheap omni-modality model serving for everyone | Documentation | User Forum | Developer Slack | Latest News 🔥 [2025/11] vLLM community officially released vllm-project/vllm-omni in order to support omni-modality models serving. About vLLM was originally designed to support large language models for text-based autoregressive generation tasks. vLLM-Omni is a framework that extends its supp…
结合LightRAG 知识库的知识图谱智能体平台。LangChain v1 + Vue + FastAPI。集成主流大模型、LightRAG、MinerU、PP-Structure、Neo4j 、联网检索、工具调用。语析 - 基于大模型的知识库与知识图谱智能体开发平台 语析是一个功能强大的智能体平台，融合了 RAG 知识库与知识图谱技术，基于 LangGraph v1 + Vue.js + FastAPI + LightRAG 架构构建。 亮点：提供全套的智能体开发套件，基于 MIT 开源协议，技术栈友好，适合基于此项目打造自己的智能体平台。 Tip详细文档请查看全新的 📄文档中心， 哔哩哔哩观看 📽️视频演示 🎉 最新动态 [2025/12/17] v0.4.0-beta 版本发布 查看详细更新日志 新增 新增对于上传附件的智能体中间件，详见文档 新增多模态模型支持（当前仅支持图片），详见文档 新建 DeepAgents 智能体（深度分析智能体），支持 todo，files 等渲染，支持文件的下载。 新增基于知识库文件生成思维导图功能（#335） …