GitHub Trends

#python

Agent Skills are reusable packages of instructions, scripts, and resources that AI agents like Codex can automatically load to complete specific tasks efficiently and consistently. Instead of repeating the same guidance repeatedly, you write a skill once and use it everywhere, which saves time and reduces errors. You can install pre-built skills automatically or create custom ones tailored to your organization's needs, then share them across teams. This modular approach transforms general AI assistants into domain specialists, enabling them to handle complex, specialized workflows reliably without requiring you to provide the same instructions in every conversation.

https://github.com/openai/skills

#typescript #agentic_workflow #ai_agent #ai_runtime #ai_sandbox #claude_code #cli #cloudflare #codex #containers #context_engineer #dev_tools #gemini_cli #react #sandbox #typescript

VM0 is a natural language agent that runs workflows automatically 24/7 in secure cloud sandboxes. It offers isolated Claude Code execution, 35,000+ skills for tools like GitHub and Notion, persistent chats with resume/fork options, and full logs/metrics for monitoring. Quick start via `npm install -g @vm0/cli && vm0 onboard` gets you automating in 5 minutes. You benefit by saving hours on repetitive tasks like reports or data syncs, with reliable, observable runs anytime.

https://github.com/vm0-ai/vm0

#python

AI-assisted code review prompts by Linux kernel expert Chris Mason speed up Linux kernel and systemd patch reviews. Install easily with bash scripts, then use slash commands like /kreview or /kdebug in tools like Claude—they auto-load project context, break big diffs into tasks, cut token costs by 40-60%, and catch more bugs. You benefit by reviewing code 30-50% faster, saving money, reducing burnout, and improving quality without replacing human checks. Works with GPT-4, Claude, and more; pairs best with semcode for navigation.

https://github.com/masoncl/review-prompts

#shell #ai_agents #ai_coding #claude #claude_code #project_management #vibe_coding

Claude Code PM is a workflow that turns product ideas into GitHub issues and code using spec-driven steps, parallel AI agents, and commands like /pmepic-oneshot to break tasks, and /pm:issue-start for execution. It preserves context, enables team collaboration via GitHub, and ensures every code line traces to specs. You benefit by shipping 3x faster, cutting bugs 75%, reducing context loss 89%, and working with multiple agents simultaneously for higher productivity.

https://github.com/automazeio/ccpm

#python

nanochat lets you train your own GPT-2 level LLM—like a basic ChatGPT—for just $73 in 3 hours on an 8xH100 GPU node using the simple speedrun.sh script. It handles tokenization, pretraining, finetuning, evaluation, inference, and a web chat UI in minimal, hackable code. You benefit by easily building, customizing, and chatting with your personal AI on a tiny budget, learning LLM mechanics hands-on without complex setups.

https://github.com/karpathy/nanochat

#go #cross_seed #cross_seeding #go #golang #libtorrent #qbit #qbittorrent #workflows

qui is a fast, modern web interface for qBittorrent that lets you manage multiple instances from one lightweight app with no dependencies—just download and run. Key features include multi-instance support, cross-seeding to match torrents across trackers, rule-based automations, backups, and a responsive UI for large collections, accessible at http7476 via simple Linux or Docker setup. This benefits you by simplifying torrent management, boosting performance, enabling automations, and saving time on handling big libraries from a single, efficient dashboard.

https://github.com/autobrr/qui

#typescript #ai_agents #claude_code #codex #generative_ai #opencode

Maestro is a free desktop app that lets you run multiple AI coding agents like Claude Code, OpenAI Codex, and OpenCode in parallel on your projects. Use keyboard shortcuts for fast control, Git worktrees for isolated branches, Auto Run playbooks for 24-hour unattended tasks, group chats to coordinate agents, and mobile access to monitor from your phone. It boosts your productivity by enabling true parallel development without conflicts, saving time on juggling projects, and keeping you in flow state for faster coding and automation.

https://github.com/pedramamini/Maestro

#swift #ai #claude_code #codex #swift

CodexBar is a tiny macOS 14+ menu bar app that shows real-time usage limits, session and weekly resets for AI tools like Codex, Claude, Cursor, Gemini, Copilot and more, with dynamic icons, toggles, and privacy-focused local processing. Download from GitHub or Homebrew, enable providers in settings, and add auth like cookies or CLI. It helps you avoid surprise token limits, track quotas without workflow breaks, and manage costs efficiently.

https://github.com/steipete/CodexBar

#python #audio_driven_talking_face #dance_generation #end_to_end_filming #long_video_generation #video_diffusion_transformers

Stable Video Infinity (SVI) lets you create videos of any length—from seconds to minutes or infinite—starting from one image and text prompts, with no quality loss, drift, or repetition. It uses error-recycling to fix mistakes automatically, supporting stories, cartoons like Tom & Jerry (up to 10+ minutes), talking heads with audio, dancing from skeletons, and multi-scene films. Everything is open-source with models, scripts, datasets, and ComfyUI workflows on Hugging Face and GitHub—you can download, run demos, or train your own easily. This saves you time and effort for pro filmmaking or fun animations without limits.

https://github.com/vita-epfl/Stable-Video-Infinity

#typescript #remote #terminal #vibecoding

VibeTunnel turns your Mac terminal into a browser-accessible interface. Use the `vt` command to run any shell command—like `vt npm run dev` or `vt --shell`—and view live output at localhost Monitor long builds, check AI agents on the go, or share sessions easily without SSH hassle.

https://github.com/amantus-ai/vibetunnel

#rust #git #git_hooks #pre_commit

prek is a faster, dependency-free alternative to pre-commit, built in Rust. You download a single binary with no runtime requirements, and it automatically manages Python versions and virtual environments for you. It runs multiple times faster than pre-commit while using half the disk space, shares toolchains between hooks, and supports parallel execution. prek is fully compatible with existing pre-commit configurations, includes built-in support for monorepos, and offers improved commands like running hooks on specific directories or last commits. Major projects like CPython, Apache Airflow, and FastAPI already use it, making it a reliable choice for streamlining your code quality checks.

https://github.com/j178/prek

#lua

99 is an alpha Neovim plugin for skilled coders that streamlines AI requests using OpenCode. Install via Lazy with the given Lua config, set keymaps like `<leader>9f` to fill functions, `<leader>9v` for visual AI edits (visual mode only), and `@` for cmp skill autocompletion from custom SKILL.md rules or AGENT.md files. View logs with `:lua require("99").view_logs()`. It boosts your workflow by keeping AI help inside Neovim for fast, restricted code generation without leaving your editor.

https://github.com/ThePrimeagen/99

#shell #claude_code #mcp #skills

Claude Code Plugins Directory offers high-quality plugins to extend Claude Code with custom commands, agents, skills, and hooks. Install easily via `/plugin install {plugin-name}@claude-plugin-directory` or browse in `/plugin > Discover`. Internal ones from Anthropic are in `/plugins`; external from partners in `/external_plugins`. Each has a standard structure with `plugin.json` metadata. This helps you customize workflows, automate tasks, and boost coding productivity across projects.

https://github.com/anthropics/claude-plugins-official

#typescript #investigation #osint #python #recon

Flowsint is a free, open-source tool for OSINT investigations that visualizes data like domains, IPs, emails, phones, crypto wallets, and websites as interactive graphs to spot hidden links fast. Install easily with Docker and Make via git clone and "make prod," then run locally at localhost:5173 for full privacy—all data stays on your machine. With 30+ auto-enrichers (e.g., subdomain scans, WHOIS, breach checks), it chains tasks to automate deep recon, saving hours on manual work and revealing patterns for cybersecurity, journalism, or fraud probes ethically.

https://github.com/reconurge/flowsint

#go

Mermaid-ascii lets you render Mermaid graphs and sequence diagrams as ASCII art right in your terminal. Install via GitHub binary, build with Go, Nix, or Docker; use commands like `mermaid-ascii -f file.mermaid` for left-to-right/top-down layouts, labels, colors, padding, or web interface. It supports directions, edges, participants, Unicode, and ASCII mode. This helps you quickly view diagrams without browsers or images, making code reviews, docs, and terminal workflows faster and easier.

https://github.com/AlexanderGrooff/mermaid-ascii

#javascript #atari_lynx #atari2600 #atari7800 #ds #emulation #emulator #emulatorjs #gameboy #n64 #nes #nintendo #nintendo_game_boy #playstation #retroarch #retroarch_wasm #sega_cd #sega_mega_drive #sega_saturn #snes #virtualboy

EmulatorJS is a free, open-source web-based emulator that lets you play classic games from Nintendo, Sega, Atari, and other systems directly in your browser without downloading software. It offers save states to resume games where you left off, customizable controls for keyboards and gamepads, and screen recording to share gameplay. The emulator runs entirely in your browser using JavaScript, supports multiple languages, and can be easily embedded into websites. You benefit from instant access to retro gaming across devices, no installation required, and the ability to build your own self-hosted gaming collection.

https://github.com/EmulatorJS/EmulatorJS

#javascript #javascript #katex #latex #math #math_typesetting

KaTeX is a fast, easy-to-use JavaScript library that displays mathematical equations on websites. It renders math instantly without slowing down your page and produces professional-quality output based on TeX, the standard for math typesetting. Unlike heavier alternatives, KaTeX has no dependencies, works across all major browsers, and can be rendered on servers before sending to users. This means your website loads faster while still showing beautiful, correctly formatted math expressions. You can use it by simply adding a few lines of code to your HTML, making it ideal for educational sites, documentation, or any web content featuring mathematical formulas.

https://github.com/KaTeX/KaTeX

#java #4k #android #bandcamp #download_videos #newpipe #peertube #soundcloud #translation #video #watch #youtube_video

NewPipe is a free, open-source Android app for ad-free streaming and downloading videos/audio from YouTube, SoundCloud, PeerTube and more, with background play, pop-up mode, subscriptions without accounts, and no Google tracking for full privacy. The team is rewriting the code for a modern, stable version—download nightly builds to try new features early. This benefits you by saving data/battery, enabling offline/multitasking use, and protecting your data on any device.

https://github.com/TeamNewPipe/NewPipe

#javascript

No description

https://github.com/anomalyco/opencode-anthropic-auth

#other #playwright

Playwright CLI is a simple command-line tool for browser automation that works best with coding agents like Claude or GitHub Copilot. Install it globally with `npm install -g @playwright/cli@latest`, then use commands like `open`, `type`, `click`, `screenshot` to control browsers efficiently without loading heavy page data. It saves tokens for faster AI tasks on large codebases. You benefit by automating web tests, taking screenshots, and managing sessions quickly, making your coding and testing workflows smoother and more reliable.

https://github.com/microsoft/playwright-cli