#logos #downloader #ios #jailbreak #sponsorblock #tweak #youtube

YouTube Plus enhances the iOS YouTube app with over 100 options like downloading videos/audio/thumbnails, copying info, customizing interfaces (remove feeds, OLED mode), player gestures, built-in SponsorBlock, and tweaks for 4K, PiP, dislikes, and quality selector. Build your custom version via GitHub Actions using a decrypted YouTube IPA—fork the repo, run the workflow, select tweaks, and download from releases (last free v5.2b4). This gives you a tailored, ad-free experience with premium features for better viewing and saving content.

https://github.com/dayanch96/YTLite

#typescript #agent #agentic_rag #ai_coding #claude_code #code_generation #code_search #cursor #embedding #gemini_cli #mcp #merkle_tree #nodejs #openai #rag #semantic_search #typescript #vector_database #vibe_coding #voyage_ai #vscode_extension

Claude Context is a plugin that adds semantic code search to Claude Code and other AI tools, using your full codebase as context via a vector database like Zilliz Cloud. It finds relevant code instantly with natural language queries, indexes efficiently (only changed files), and cuts token use by ~40% for the same quality. You save costs on large projects, get precise results without loading whole files, and code faster with deep, relevant context across millions of lines. Setup needs free Zilliz/OpenAI keys and Node.js 20+; works with VS Code, Cursor, and more.

https://github.com/zilliztech/claude-context

#other #agent_skills #ai_agents #antigravity_skills #awesome #awesome_list #awesome_lists #claude_code #claude_code_skills #claude_skills #codex_skills #cursor_skills #gemini_skills #opencode_skills #skills

This curated collection offers over 1100 hand-picked Agent Skills from top teams like Anthropic, Google, Vercel, Stripe, Cloudflare, Microsoft, OpenAI, and Figma, plus community gems for coding, security, marketing, and more—compatible with Claude Code, Codex, Cursor, and others. Unlike AI-generated junk, these are real-world tools for tasks like document editing, cloud deployments, auth setups, and PM workflows. You'll save hours debugging, boost code quality, and ship faster with expert guidance directly in your AI tools.

https://github.com/VoltAgent/awesome-agent-skills

#typescript #analytics #autogen #evaluation #langchain #large_language_models #llama_index #llm #llm_evaluation #llm_observability #llmops #monitoring #observability #open_source #openai #playground #prompt_engineering #prompt_management #self_hosted #ycombinator

Langfuse is a free, open-source platform to build, monitor, evaluate, and debug AI apps using large language models (LLMs). It offers tracing for app logic, prompt management, evaluations, datasets, a playground, and easy integrations like OpenAI, LangChain, and LlamaIndex. Deploy it on Langfuse Cloud (free tier) or self-host with Docker in minutes. This helps you quickly spot issues, improve prompts without slowing apps, test reliably, and speed up development—saving time and boosting AI performance.

https://github.com/langfuse/langfuse

#python #aigc #comfyui #image_generation #tts #video_generation

Pixelle-Video is an AI tool that fully automates short video creation: input a theme, and it writes scripts, generates images/videos, adds voiceovers, music, and compiles the final clip—no editing skills needed. Recent updates include action transfer, multi-language TTS, and custom uploads for personalized results. Download the Windows package or install via source for easy web use with free local options. You benefit by quickly making pro videos for social media or content, saving hours of manual work and costs.

https://github.com/AIDC-AI/Pixelle-Video

#typescript

Skills CLI lets you easily add, list, update, remove, find, or create reusable instruction sets (in SKILL.md files) for 40+ coding agents like OpenCode, Claude Code, Cursor, and Roo Code. Install with `npx skills add vercel-labs/agent-skills` (use flags like -g for global, --list to preview, --all for everything). This boosts your agents by giving specialized guidance for tasks like PRs, release notes, or tool integrations, saving time on repetitive work and improving code quality across projects.

https://github.com/vercel-labs/skills

#javascript #ai_art_generator #ai_image_generation #ai_video_generation #creative_tools #flux_1 #generative_ai #higgsfield #higgsfield_ai #higgsfield_alternative #image_to_video #javascript #kling_ai #midjourney_alternative #muapi #open_source #sora_alternative #text_to_video #uncensored #unrestricted #wan_video

Open Generative AI is a free, open-source tool for creating AI images, videos, lip syncs, and cinema with 200+ models like Flux and Kling. Unlike paid apps with filters and limits, it has no content blocks, subscriptions, or data sharing—you get full creative freedom, self-hosting, and local generation on your device. Try it online at dev.muapi.ai/open-generative-ai or download desktop apps for Mac, Windows, or Linux. This saves money, protects privacy, and lets you make unrestricted art fast.

https://github.com/Anil-matcha/Open-Generative-AI

#python

ML Intern is an autonomous AI agent that researches, writes, and deploys high-quality machine learning code using Hugging Face tools, docs, datasets, and cloud resources. Install easily by cloning the GitHub repo, running `uv sync`, and setting API keys in a `.env` file; use interactively with `ml-intern` or headless like `ml-intern "fine-tune llama on my dataset"`. This saves you hours of manual ML work, letting you quickly prototype and ship projects without deep expertise.

https://github.com/huggingface/ml-intern

#javascript #claude #codex #marketing

Marketing Skills for AI Agents offers markdown files with specialized workflows for AI agents to handle tasks like SEO audits, copywriting, CRO, paid ads, analytics, and growth strategies. All skills build on a core product-marketing-context file and cross-reference each other for better results. Install easily via CLI (e.g., `npx skills add coreyhaines31/marketingskills`), Claude Code, or git, then ask your agent to optimize pages or write emails—it works with Claude, Cursor, and more under a permissive MIT license. This saves you time on marketing, boosts conversions and growth using proven best practices.

https://github.com/coreyhaines31/marketingskills

#python

Free Claude Code lets you use Claude Code CLI and VSCode for free without an Anthropic API key. It proxies requests to free providers like NVIDIA NIM (40 req/min), OpenRouter free models, DeepSeek, or local LM Studio/llama.cpp. Just set 2 env vars, edit .env with your keys/models, run the server on port 8082, and point Claude to it—works seamlessly with thinking tokens, tool parsing, and rate limits. You save money on API costs, get unlimited local options for privacy/offline coding, and mix providers for top performance.

https://github.com/Alishahryar1/free-claude-code

#typescript #antigravity #claude #claude_code #claude_code_hooks #claude_code_plugins #claude_code_skill #codex #codex_cli #context_mode #copilot #cursor_plugin #kiro #mcp #mcp_server #mcp_tools #openclaw #opencode #pi_agent #skills #zed_extension

Context Mode is an MCP server that fixes context window overload in AI coding tools by sandboxing raw data (like 56KB snapshots or logs) outside chats—shrinking 315KB to 5.4KB (98% savings), tracking sessions in SQLite for seamless resumes after compaction, and making LLMs generate code for analysis instead of dumping data. It installs easily on 12 platforms (Claude Code, Cursor, etc.) with hooks for auto-routing. You benefit by extending sessions 6x longer, picking up tasks instantly without re-explaining, and boosting productivity on big repos or logs.

https://github.com/mksglu/context-mode

#python #api #ddgs #dht #mcp #mcp_server #metasearch #p2p #python #search #websearch

DDGS is a Python library (version 3.10+) for metasearch that pulls text, images, videos, news, and books from engines like Bing, DuckDuckGo, and Google. Install with `pip install ddgs`, use `DDGS().text("query")` for fast results, or run API/CLI servers for web access; optional DHT (Linux/macOS) shares anonymous caches to cut latency 90% and dodge rate limits. It benefits you by delivering quick, diverse, aggregated search data without single-engine restrictions or slow repeats—ideal for apps, scripts, or tools needing reliable info fast.

https://github.com/deedy5/ddgs

#typescript

Roo Code is a free, open-source VS Code extension that acts as your AI-powered dev team. It generates code from natural language, refactors, debugs, answers codebase questions, and automates tasks using modes like Code, Architect, Ask, and Debug. A community team now maintains it after 3 million installs, adding GPT-5.5, Claude Opus 4.7 support, and easy checkpoint navigation. This boosts your coding speed, cuts errors, saves time on repetitive work, and keeps you in flow without switching tools—helping you build faster and smarter.

https://github.com/RooCodeInc/Roo-Code

#python

Universal Commerce Protocol (UCP) is an open standard that lets AI agents, apps, businesses, payment providers, and others communicate seamlessly for secure checkouts, order updates, and personalized shopping without custom integrations. Key features include dynamic capability discovery, composable modules like Checkout and Identity Linking, transport flexibility, and strong security. You benefit by easily building agentic commerce, automating discoveries and transactions to boost efficiency, cut integration costs, and deliver better customer experiences across platforms.

https://github.com/Universal-Commerce-Protocol/ucp

#python #awesome #awesome_lists #awesome_resources #codex #codex_cli #codex_skills #coding_agent_skills #coding_agents #gpt_5_1_codex #gpt_5_codex #llm #skills

Awesome Codex Skills offers a curated list of practical skills to automate workflows in Codex CLI and API, like code reviews, meeting summaries, GitHub PR fixes, Notion organization, email drafting, and data analysis across 1000+ apps via Composio. Install easily with a Python script or manually by copying folders to ~/.codex/skills, then restart Codex—it auto-triggers skills matching your task description. This saves you hours on repetitive dev, productivity, and comms tasks, letting Codex take real actions like posting to Slack or creating issues for faster, smarter work.

https://github.com/ComposioHQ/awesome-codex-skills

#go #api #claude_api #deepseek #deepseek_api #docker #freeapi #go #openai_api #proxy #proxy_server #react #vercel #vercel_deployment #zeabur

DS2API turns DeepSeek web chat into APIs compatible with OpenAI, Claude, and Gemini, using Go backend and React web UI for easy management. It supports multi-account rotation, concurrency queues, tool calling, and models like deepseek-chat/reasoner with aliases (e.g., gpt-5). Deploy simply via release binaries, Docker, Vercel, or source—edit config.json with your keys/accounts and run. You benefit by accessing DeepSeek affordably through familiar SDKs, saving costs and simplifying integration for apps or testing.

https://github.com/CJackHwang/ds2api

#shell

Agent Skills boost your coding with easy-to-add tools for planning (like turning chats into PRDs or GitHub issues), development (TDD for bugs, refactoring), and setup (pre-commit hooks, git safety). Use simple commands like `npx skills@latest add mattpocock/skills/to-prd` to install. They save time by automating smart planning, clean code, and note management in Obsidian vaults, helping you build faster without errors or hassle.

https://github.com/mattpocock/skills

#go #agents #claude_code #coding

Beads (bd) is a free CLI tool for macOS, Linux, Windows, and FreeBSD that gives AI coding agents persistent, structured memory via a version-controlled Dolt SQL database with graphs for tasks, dependencies, and hierarchies. Install once with `curl` script or brew, then `bd init` in any project—no repo cloning needed. Key commands like `bd ready`, `bd create`, and `bd update` track blockers, claim tasks, and auto-detect ready work in JSON for agents. It prevents conflicts with hash IDs, compacts old tasks, and supports stealth/git-free modes. You benefit by replacing messy plans with clear, long-term task tracking that keeps AI agents focused without losing context, boosting productivity on complex projects.

https://github.com/gastownhall/beads

#typescript #bitcoin #bitcoin_node #lightning_node #p2p #personal_server #privacy_enhancing_technologies #self_hosting

StartOS is a free, open-source Linux OS for your personal server. It easily sets up services like Bitcoin nodes, Lightning, Matrix chat, Nextcloud storage, and more from its Marketplace—running them safely in isolated containers with backups, updates, and monitoring. Buy a ready Start9 server or install on your hardware. This gives you full data control, no cloud reliance, better privacy, and ownership of your tech for secure self-hosting.

https://github.com/Start9Labs/start-os

#python #adb #android #android_mods #no_root #rootless #shizuku

Shizuku lets normal apps use powerful system features on non-rooted Android devices via ADB, with this curated list showcasing apps for automation (like Tasker), file management (MiXplorer), customization (DarQ), privacy, audio tweaks, and more across categories like AI agents and gaming. It helps you unlock advanced controls, boost productivity, enhance privacy, and customize your phone without rooting, saving time and extending device capabilities safely.

https://github.com/timschneeb/awesome-shizuku