#python

Slime is a high-performance framework for post-training large language models with reinforcement learning (RL). It connects Megatron for fast training and SGLang for data generation, powering top models like GLM-4.7, Qwen3, DeepSeek V3, and Llama 3. You get efficient, flexible RL workflows with customizable data tools, cutting training time and boosting model accuracy for research or production—saving resources while achieving breakthrough results in physics, agents, and code generation.

https://github.com/THUDM/slime

#python

WiFi DensePose uses WiFi signals and AI to detect human poses in real-time without cameras, tracking up to 10 people at 30 FPS with sub-50ms speed. Its Rust version boosts performance 810x faster, adds fall detection, activity tracking, and a disaster module for finding survivors under rubble via vital signs and 3D location. Install easily with `pip install wifi-densepose` for privacy-safe monitoring in homes, fitness, healthcare, or emergencies—saving lives and enhancing security without visual privacy risks.

https://github.com/ruvnet/wifi-densepose

#python #adblock #adblock_list #adblock_plus #adguard #adguard_list #adguardhome #quantumult_x

GOODBYEADS offers powerful, regularly updated rules (over 215,000 ad blocks, 102,000 DNS blocks) in formats like AdGuard, Quantumult X, and SmartDNS, with GitHub and fast domestic links. It blocks ads, trackers, and malware from top sources for clean browsing. You gain faster page loads, better privacy, less data use, and fewer distractions on any device.

https://github.com/8680/GOODBYEADS

#python

This Claude Code Telegram Bot connects your Telegram messenger to Claude AI, letting you work with your code projects from anywhere without needing a terminal. You can chat naturally with Claude to analyze, edit, or explain your code, run tests, and manage files—all from your phone. The bot maintains conversation history for each project, so Claude remembers context between chats. It includes security features like user authentication and directory protection, plus it can handle webhooks and scheduled tasks. The main benefit is productivity on the go: you get AI-powered coding assistance instantly through a messaging app you already use daily, transforming your phone into a development tool.

https://github.com/RichardAtCT/claude-code-telegram

#python #bytetrack #multi_object_tracking #oc_sort #sort

Trackers is a simple Python library (pip install trackers) for multi-object tracking that plugs into any detection model like YOLO. Use it via CLI on videos/webcams or in Python code with trackers like ByteTrack (top performer on MOT17/SportsMOT benchmarks) to add labels and trajectories. Evaluate with MOT metrics too. Benefit: Quickly add reliable object tracking to your computer vision projects for real-time apps like traffic or sports analysis, saving time on custom code.

https://github.com/roboflow/trackers

#python

Hugging Face Skills are ready-to-use folders with instructions, scripts, and tools for AI agents to handle tasks like creating datasets, training models, running evaluations, managing jobs, and publishing papers. They work seamlessly with tools like Claude Code, OpenAI Codex, Gemini CLI, and Cursor—just install via simple commands and mention the skill in your instructions, such as "Use the HF model trainer skill." This saves you time by automating complex Hugging Face Hub operations, letting your agent execute them accurately without manual coding.

https://github.com/huggingface/skills

#python #agents #claude #cursor #databricks #vibecoding

The Databricks AI Dev Kit enhances AI-driven development by providing your coding assistant (Claude Code, Cursor, etc.) with trusted Databricks knowledge and best practices. It includes a Python library, MCP server with 50+ tools, markdown skills teaching Databricks patterns, and a web-based builder app. You can build Spark pipelines, jobs, dashboards, knowledge assistants, and deploy ML models faster and smarter. The benefit is that your AI coding assistant gains direct access to Databricks functionality and patterns, enabling you to develop data and AI applications more efficiently with built-in governance and best practices.

https://github.com/databricks-solutions/ai-dev-kit

#python

Agent Skills for Context Engineering offers free, open skills to master context engineering—curating AI model inputs like prompts, tools, history, and docs for top performance despite limited attention. Learn fundamentals, architectures (multi-agent, memory), tools, evaluation, and new skills like hosted agents and BDI mental states via Claude Code plugins or any platform. Examples include digital brain OS and book-writing pipelines. You gain reliable AI agents that cut errors, boost speed (up to 55% faster tasks), reduce costs, and deliver accurate results for projects.

https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering

#python

PersonaLive creates real-time portrait animations from a single image, using driving videos for expressive faces and head moves. It runs on a 12GB GPU for infinite-length videos, with easy web UI for live streaming or offline generation, plus ComfyUI and TensorRT speed boosts. You get smooth, high-quality animations fast for streams, content, or art—up to 22x quicker than others, saving time and hardware costs.

https://github.com/GVCLab/PersonaLive

#python #ai #ai_scraping #automation #crawler #crawling #crawling_python #data #data_extraction #mcp #mcp_server #playwright #python #scraping #selectors #stealth #web_scraper #web_scraping #web_scraping_python #webscraping #xpath

Scrapling is a fast Python web scraping tool that fetches pages, bypasses anti-bot blocks like Cloudflare, and adapts to site changes by auto-finding elements. Use simple CSS/XPath selectors, spiders for big crawls with pause/resume, proxy rotation, and CLI—no code needed sometimes. Install via pip; it's memory-light and beats others in speed. You save time fixing broken scrapers, scrape reliably at scale, cut costs with AI tools, and focus on using data for leads, prices, or research.

https://github.com/D4Vinci/Scrapling

#javascript #ai #algorithm #artificial_intelligence #chatgpt #claude #cursor #deep_learning #deepseek #gemini #generative_ai #gpt #llm #mcp #openai #python #rag #vibe_coding #vibecoding #vue #vuepress

鱼皮的 AI知识库 offers a free Vibe Coding tutorial for beginners, teaching AI-powered programming with natural language prompts to build and monetize apps fast—no coding skills needed. It covers tools, projects, tips, and paths like making your first work in 10 minutes, plus AI guides on DeepSeek, Cursor, and more. You benefit by quickly creating profitable products, breaking tech barriers, and enjoying AI perks to improve life and work. Start at ai.codefather.cn/vibe.

https://github.com/liyupi/ai-guide

#typescript #agent #agentic #agentic_framework #agentic_workflow #ai #ai_agents #bytedance #deep_research #harness #langchain #langgraph #langmanus #llm #multi_agent #nodejs #podcast #python #superagent #typescript

DeerFlow 2.0 is an open-source super agent harness that orchestrates multiple sub-agents, memory systems, and sandboxed execution environments to accomplish complex tasks. Built on LangGraph and LangChain, it combines research, coding, and content creation capabilities with extensible skills and tools. The platform features isolated Docker containers for safe execution, long-term memory that learns your preferences, and the ability to spawn sub-agents that work in parallel on different task angles. You benefit from dramatically reduced research and automation time—tasks that typically take hours complete in minutes—while maintaining full transparency and control over agent decisions through human-in-the-loop collaboration. Whether you need deep research reports, data analysis, slide decks, or custom workflows, DeerFlow handles multi-step complexity without requiring extensive coding knowledge.

https://github.com/bytedance/deer-flow

#typescript #agent #agent_development #ai_agent #claude #claude_code #educational #llm #python #teaching #tutorial

Claude Code is an AI agent framework that uses a simple loop: send messages to Claude, check if it needs tools, execute those tools, and repeat. The benefit is that you can build powerful autonomous agents by layering one feature at a time—from basic tool use to multi-agent teams—without rewriting the core loop. This modular approach lets you start simple with bash commands and scale to complex workflows with planning, skill loading, background tasks, and team coordination, making it easier to automate development work and delegate entire projects to AI agents.

https://github.com/shareAI-lab/learn-claude-code

#python #ai #ai_agent #ai_infra #kubernetes #sandbox

OpenSandbox is a general-purpose sandbox platform that lets you safely run AI applications, code, and agents in isolated environments. It provides multi-language SDKs for Python, Java, and JavaScript, making it easy to integrate into your projects. The platform supports Docker and Kubernetes runtimes, so you can run sandboxes locally or at scale. Key benefits include running code generated by AI models safely, executing data analysis, automating browser tasks, and training AI systems without risking your main system. Whether you're building coding agents, testing applications, or letting AI handle complex tasks, OpenSandbox gives you a secure, controlled space to experiment and execute code without side effects.

https://github.com/alibaba/OpenSandbox