Github Top Repositories

📌 Spotted on GitHub Trending: Open-LLM-VTuber/Open-LLM-VTuber — let's break it down. 🔗 https://github.com/Open-LLM-VTuber/Open-LLM-VTuber 📝 Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms ────────────────────────────── Open-LLM-VTuber is a voice-interactive AI companion that supports real-time voice conversations and visual perception. It features a lively Live2D avatar and can run completely offline on your computer. The project offers cross-platform support for Windows, macOS, and Linux, and has two usage modes: web version and desktop client. The desktop client has a transparent background desktop pet mode, allowing the AI companion to accompany you anywhere on your screen. It also supports advanced interaction features like visual perception, voice interruption, touch feedback, and Live2D expressions. Key technical highlights include extensive model support for Large Language Models, Automatic Speech Recognition, and Text-to-Speech, as well as high customizability through simple module configuration, character customization, and flexible Agent implementation. The project is suitable for users looking for a personalized AI companion and developers interested in contributing to or customizing the project. Get your own AI companion today - it's like having a virtual friend by your side! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 supermemoryai/supermemory landed on trending. Worth a proper look. 🔗 https://github.com/supermemoryai/supermemory 📝 Memory engine and app that is extremely fast, scalable. The Memory API for the AI era. ────────────────────────────── Supermemory is a state-of-the-art memory and context engine for AI that automatically learns from conversations, extracts facts, builds user profiles, and handles knowledge updates. It's designed to give AI tools a persistent memory graph across every conversation, making them smarter over time. With Supermemory, you can use it as a company or personal brain, and it's available as a single API for developers to add memory, RAG, user profiles, and connectors to their agents and apps. The key features include: - Memory: extracts facts from conversations and handles temporal changes, contradictions, and automatic forgetting - User Profiles: auto-maintained user context with stable facts and recent activity - Hybrid Search: combines RAG and memory in a single query - Connectors: auto-sync with real-time webhooks from Google Drive, Gmail, Notion, and more To get started, you can use the Supermemory app, browser extension, or plugins for various AI tools. For developers, it's easy to integrate with a single API and drop-in wrappers for major AI frameworks. Supermemory is also state of the art across major AI memory benchmarks, including LongMemEval, LoCoMo, and ConvoMem. In short, Supermemory gives your AI the power of human-like memory - it remembers, so you don't have to. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

1,000,000 USDT awaits you! Toobit Ready to win 1,000,000 usdt rewards? Come to join Win the World event on Toobit. Ad. 18+

🚀 Meet jamwithai/production-agentic-rag-course: a gem from today's GitHub trending list. 🔗 https://github.com/jamwithai/production-agentic-rag-course 📝 No description. ────────────────────────────── The jamwithai/production-agentic-rag-course is a hands-on project where you'll build a complete research assistant system that automatically fetches academic papers, understands their content, and answers your research questions using advanced RAG techniques. This course is designed for learners who want to master AI engineering skills, particularly in building production-grade RAG systems. The system, called The arXiv Paper Curator, uses a foundation-first approach, starting with keyword search foundations and then enhancing with vector search for hybrid retrieval. Key features include: - Automated data pipeline fetching and parsing academic papers from arXiv - Production BM25 keyword search with filtering and relevance scoring - Intelligent chunking and hybrid search combining keywords with semantic understanding - Complete RAG pipeline with local LLM, streaming responses, and Gradio interface - Production monitoring with Langfuse tracing and Redis caching for optimized performance - Agentic RAG with LangGraph and Telegram Bot for mobile access Technical highlights include:

Docker, FastAPI, PostgreSQL, OpenSearch, and Airflow

The course is structured into 7 weeks, each focusing on a different aspect of building a production RAG system. In summary, this course is perfect for those who want to build modern AI systems from the ground up and master in-demand AI engineering skills. Takeaway: Building a production RAG system is not just about AI, it's about creating a robust search foundation first. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet stefan-jansen/machine-learning-for-trading: a gem from today's GitHub trending list. 🔗 https://github.com/stefan-jansen/machine-learning-for-trading 📝 Code for Machine Learning for Algorithmic Trading, 2nd edition. ────────────────────────────── The stefan-jansen/machine-learning-for-trading GitHub repository is a treasure trove of resources for anyone looking to apply machine learning to trading. The repo is based on a book that aims to provide a practical and comprehensive guide to using machine learning in algorithmic trading. With over 150 notebooks, the repository offers a wealth of examples and code to help readers implement the concepts and techniques discussed in the book. The repository covers a wide range of topics, including data sourcing, financial feature engineering, and portfolio management. It also explores the use of supervised and unsupervised machine learning algorithms for trading, as well as deep learning models like CNN and RNN. The notebooks provide numerous examples of how to work with and extract signals from market, fundamental, and alternative text and image data. To get the most out of the repository, readers are encouraged to review the notebooks while reading the book. The notebooks are usually in an executed state and often contain additional information not included in the book due to space constraints. The repository also includes installation instructions and configuration files for setting up various conda environments and installing the packages used in the notebooks. The target audience for this repository includes traders, data scientists, and developers interested in applying machine learning to trading. Whether you're a beginner or an experienced practitioner, the repository has something to offer. So why not join the ML4T Community and start exploring the world of machine learning for trading? In short, this repository is a must-visit for anyone looking to leverage machine learning for trading strategies - learn by doing, and trade with code. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 OpenBMB/VoxCPM is trending — and it deserves your attention. 🔗 https://github.com/OpenBMB/VoxCPM 📝 VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning ────────────────────────────── VoxCPM2 is a tokenizer-free Text-to-Speech system that generates continuous speech representations via an end-to-end diffusion autoregressive architecture. It supports 30 languages, voice design, controllable voice cloning, and 48kHz studio-quality audio output. Key features include: - Multilingual support: Input text in any of the 30 supported languages and synthesize directly, no language tag needed - Voice design: Create a brand-new voice from a natural-language description alone - Controllable cloning: Clone any voice from a short reference clip, with optional style guidance - 48kHz high-quality audio: Directly outputs 48kHz studio-quality audio via AudioVAE V2's asymmetric encode/decode design To get started, you can install VoxCPM using pip install voxcpm and use the Python API to generate speech. There's also a CLI for voice design, controllable voice cloning, and ultimate cloning. The project is fully open-source & commercial-ready under the Apache-2.0 license. For high-throughput serving, consider using Nano-vLLM-VoxCPM or vLLM-Omni for production multi-tenant deployments. In short, VoxCPM2 is a game-changer for multilingual speech synthesis, offering unparalleled naturalness and expressiveness - give it a try and hear the difference for yourself! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🌟 reconurge/flowsint caught my eye on GitHub Trending today. 🔗 https://github.com/reconurge/flowsint 📝 A modern platform for visual, flexible, and extensible graph-based investigations. For cybersecurity analysts and investigators. ────────────────────────────── Introduction to Flowsint: Flowsint is an open-source OSINT graph exploration tool designed for ethical investigation, transparency, and verification. The tool allows users to explore relationships between entities through a visual graph interface and automated enrichers. Key Features: - Graph-based investigation - Visual graph interface - Automated enrichers for domains, IPs, social media, and more - Support for multiple data types, including domains, IPs, ASNs, and more Usage: To get started with Flowsint, users need to install the required prerequisites, including Docker and Make. The tool can be installed by running the command:

git clone https://github.com/reconurge/flowsint.git
cd flowsint
make prod

Then, users can access the tool at http://localhost:5173/register and create an account. Technical Highlights: - Modular structure with separate modules for core utilities, enrichers, API, and frontend application - Support for multiple databases, including PostgreSQL and Neo4j - Authentication and authorization mechanisms - Real-time event streaming Audience: Flowsint is designed for cybersecurity researchers and analysts, journalists and OSINT investigators, law enforcement or fraud investigation teams, and organizations conducting internal threat intelligence or digital risk analysis. Remember: Flowsint must be used strictly for lawful, ethical investigation and research purposes. Any misuse of this software is strictly prohibited. Here's the punchy one-liner takeaway: Flowsint is a game-changing OSINT tool that helps investigators uncover hidden relationships and stay one step ahead of threats. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚨 ONLY THE FIRST 5 GET THIS. I'm sharing this link with my network once — and only the first 5 people who enroll through it lock in a deal that has never been offered before. 👑 Lifetime access to HelloEncyclo — every AI, ML & Data Science course ever built — for ~$41. Once. Forever. This isn't a drill. This isn't a rerun. This is the founding-member price — and it disappears the moment the first 250 seats globally are gone. ✅ 13 courses live right now ✅ 40+ more in 2–3 weeks ✅ Every future course included automatically ✅ 15-day money-back — full refund, no questions Code: PRESALE-BOOK-WAVE-2GFG (Log in with Gmail · valid once · applies at checkout) 👇 First 5. That's it. https://helloencyclo.com/?ref=HUSSEINSHEIKHO ⏳ Once those 5 seats go through this link — I'm not sharing it again. 🔥

🔍 Deep-diving into nesquena/hermes-webui — fresh off the trending list. 🔗 https://github.com/nesquena/hermes-webui 📝 Hermes WebUI: The best way to use Hermes Agent from the web or from your phone! ────────────────────────────── Hermes Web UI is a lightweight, dark-themed web app interface for the Hermes Agent, a sophisticated autonomous agent that lives on your server. This web UI provides a convenient way to access the agent's features, including chat, sessions, workspace file browsing, and more, all from a web browser. Key features include a three-panel layout, model and profile controls, a circular context ring for token usage, and a Hermes Control Center for settings and session tools. The web UI also supports light mode, customizable settings, and password configuration. From a technical standpoint, Hermes Web UI is built using Python and vanilla JavaScript, with no build step, framework, or bundler required. The application is designed to be self-hosted, with support for SSH tunneling for secure access. The target audience for Hermes Web UI appears to be developers and power users who want a convenient and intuitive way to interact with the Hermes Agent from a web browser. With its robust feature set and flexible configuration options, Hermes Web UI is an attractive choice for anyone looking to get the most out of their Hermes Agent setup. In short, Hermes Web UI is a powerful tool that puts the full capabilities of the Hermes Agent at your fingertips, from anywhere, at any time - revolutionizing the way you interact with AI. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

MasterCard Without a Bank SAKURA Wallet | Virtual Mastercard Get a Mastercard in Telegram. No bank account, no paperwork. Spend USDT anywhere Mastercard is accepted. Ad. 18+

🎯 D4Vinci/Scrapling landed on trending. Worth a proper look. 🔗 https://github.com/D4Vinci/Scrapling 📝 🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! ────────────────────────────── Scrapling is an adaptive web scraping framework that streamlines the process of extracting data from websites. Its key features include an intelligent parser that learns from website changes, fetchers that bypass anti-bot systems, and a spider framework for concurrent, multi-session crawls. Key highlights of Scrapling include: - Selection methods for precise data extraction - Fetchers for bypassing anti-bot systems like Cloudflare Turnstile - Spiders for scalable, concurrent crawls - Proxy Rotation for automatic rotation of proxies Technical highlights include: - Blazing fast crawls with real-time stats and streaming - StealthyFetcher for fetching websites under the radar - DynamicFetcher for handling dynamic content Usage examples include:

from scrapling.fetchers import Fetcher, AsyncFetcher, StealthyFetcher, DynamicFetcher
StealthyFetcher.adaptive = True
p = StealthyFetcher.fetch('https://example.com', headless=True, network_idle=True)  
products = p.css('.product', auto_save=True)                                       
products = p.css('.product', adaptive=True)                                         

Audience: Web scrapers, data extraction professionals, and anyone looking to extract data from websites. Scrapling handles everything from single requests to full-scale crawls, making it an essential tool for anyone looking to extract data from the web. Scrapling in a nutshell: Scrape smarter, not harder. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: affaan-m/ECC — let's break it down. 🔗 https://github.com/affaan-m/ECC 📝 The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. ────────────────────────────── The ECC project is a harness-native operator system designed for agentic work, built from real-world multi-harness engineering workflows. It's not just about configurations, but a complete system that includes skills, instincts, memory optimization, continuous learning, security scanning, and research-first development. With 182K+ stars, 28K+ forks, and 170+ contributors, ECC supports 12+ language ecosystems and enables cross-harness agent workflows. The system is production-ready and works across various AI agent harnesses, including Codex, Claude Code, Cursor, OpenCode, Gemini, Zed, and GitHub Copilot. ECC provides a range of features, including token optimization, memory persistence, continuous learning, and security scanning. To get started, users can follow the Shorthand Guide, Longform Guide, or Security Guide, which cover setup, foundations, philosophy, and security best practices. The project also offers a dashboard GUI and a range of operator workflows, including brand-voice, social-graph-ranker, and customer-billing-ops. The ECC community is active, with discussions, sponsorship, and pro subscriptions available. The project is MIT-licensed and will remain free and open-source forever. In short, ECC is a powerful tool for agentic work that's constantly evolving to meet the needs of its users. Join the community and start building with ECC today - the future of agentic work is here! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe