Github Top Repositories

🎯 cactus-compute/needle landed on trending. Worth a proper look. 🔗 https://github.com/cactus-compute/needle 📝 14MB foundation model for tiny devices; phones, wearables, smart home, and robots. ────────────────────────────── Needle 2 is an open-source, 45M-parameter model designed for tool calling, device use, and structured extraction. It's a compact, self-contained model that runs on a single 14MB binary, using approximately 28MB of RAM. Key features include a simple contract for tool calls, confidence-gated responses, and tool retrieval capabilities. To get started, you can install the cactus-needle package using pip install cactus-needle, then describe your tools and call them from Python. The model supports fine-tuning with LoRA, allowing you to adapt it to your specific use case. The model is suitable for developers and researchers looking to integrate a compact, versatile AI model into their applications. One-liner takeaway: Needle 2 packs a punch as a tiny, 14MB model that delivers big on tool calling and structured extraction capabilities. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 ToolJet/ToolJet just hit the trending charts — here's why it matters. 🔗 https://github.com/ToolJet/ToolJet 📝 ToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀 ────────────────────────────── ToolJet is an open-source platform for building and deploying internal tools, workflows, and AI agents. It offers a visual builder with a drag-and-drop UI, integrations with databases, APIs, SaaS apps, and object storage. Key features include a built-in no-code database, multi-page apps and multiplayer editing, and 80+ data sources. To get started, you can create a ToolJet Cloud account or self-host using Docker with the following command:

docker run \
  --name tooljet \
  --restart unless-stopped \
  -p 80:80 \
  --platform linux/amd64 \
  -v tooljet_data:/var/lib/postgresql/13/main \
  tooljet/try:ee-lts-latest

ToolJet is ideal for developers, businesses, and organizations looking to streamline their workflows and build custom tools. With its extensive documentation and community support, it's easy to get started and find help when needed. One-liner takeaway: ToolJet empowers you to build and deploy custom tools and workflows with ease, making it a game-changer for businesses and developers alike. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 public-apis/public-apis is trending — and it deserves your attention. 🔗 https://github.com/public-apis/public-apis 📝 A collective list of free APIs ────────────────────────────── The public-apis/public-apis GitHub repository is a treasure trove of public APIs from various domains, manually curated by the community. It provides an extensive list of APIs that can be used for personal projects. The repository is divided into categories such as animals, anime, anti-malware, and more. Each API has its own description, authentication requirements, and HTTPS and CORS support. The repository also includes a contributing guide and a list of issues and pull requests. To get started, simply browse the list of APIs, find one that suits your needs, and start using it. With the public-apis/public-apis repository, you can unlock a world of possibilities and take your projects to the next level: start building today and never stop innovating! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: akitaonrails/ai-memory — let's break it down. 🔗 https://github.com/akitaonrails/ai-memory 📝 Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors ────────────────────────────── ai-memory is a tool that gives long-term memory to AI coding agents, allowing them to pick up where they left off, even if they're switched out for a different agent. It does this by creating a shared, persistent wiki compiled from sanitized lifecycle observations. Key features include zero-friction lifecycle capture, opt-in managed workstreams, per-repository capture exclusions, and optional per-operator memory slots. ai-memory supports a wide range of agents, including Claude Code, Codex, Command Code, and more. To use ai-memory, simply run it in the same directory as your agent, and it will take care of the rest. From a technical standpoint, ai-memory uses a git repo to store its wiki, making it easy to grep and backup. This tool is ideal for developers who use multiple AI coding agents and want to streamline their workflow. In short, ai-memory is a game-changer for AI coding agents - it's like having a personal assistant that remembers where you left off, so you can pick up right where you started! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet OpenCut-app/OpenCut: a gem from today's GitHub trending list. 🔗 https://github.com/OpenCut-app/OpenCut 📝 The open-source CapCut alternative ────────────────────────────── OpenCut is a free and open source video editor designed for web, desktop, and mobile platforms. Its key features include a Rust core for seamless performance across devices, a plugin-first architecture, and a headless mode for automation and batch rendering. The Editor API and MCP server for AI agents are also in the pipeline. To get started with development, you can install proto and use it to set up the required tools. The repository provides scripts for web:dev, api:dev, and desktop:dev environments. Although the project is not yet open to outside contributions, you can join the Discord community to follow along, ask questions, or simply hang out. OpenCut is supported by companies like fal.ai, which provides generative image, video, and audio models. One-liner takeaway: OpenCut is revolutionizing video editing with its open source, cross-platform approach, and it's definitely one to watch in the world of creator tools! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ unslothai/unsloth is making waves. Here's the full picture. 🔗 https://github.com/unslothai/unsloth 📝 Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more. ────────────────────────────── Unsloth is a revolutionary desktop app that allows you to run, train, and deploy AI models locally. With support for various types of models, including LLMs, diffusion, embedding, and audio models, Unsloth provides a comprehensive platform for AI development. Key Features: Unsloth offers a range of features, including running and training models, fine-tuning, and deploying models with support for multiple hardware configurations, including CPU, NVIDIA, AMD, and Intel. It also provides remote access to your local models through secure Cloudflare HTTPS. Usage: To get started with Unsloth, you can download the native desktop app for your operating system or install it manually using the provided installation scripts. Unsloth can be used in three ways: Unsloth Desktop, Unsloth Studio (web UI), and Unsloth Core (code-based version). Technical Highlights: Unsloth supports various backends, including PyTorch, MLX, and GGUF, allowing for flexible model deployment. It also provides tools like Claude Code, Codex, and MCP for local model usage. Audience: Unsloth is designed for developers, researchers, and AI enthusiasts who want to run, train, and deploy AI models locally. With its user-friendly interface and comprehensive documentation, Unsloth is accessible to both beginners and experienced users. Takeaway: Unsloth is the ultimate AI development platform, providing a seamless and secure way to run, train, and deploy AI models locally, making it an essential tool for anyone working with AI. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into basecamp/omarchy — fresh off the trending list. 🔗 https://github.com/basecamp/omarchy 📝 Beautiful, Modern & Opinionated Linux ────────────────────────────── Check out Omarchy, a sleek Linux distribution from Basecamp and created by DHH. It's designed to be modern and opinionated, making it a unique offering in the Linux world. To learn more, head over to omarchy.org. Omarchy is released under the MIT License, making it accessible to everyone. Whether you're a seasoned developer or just starting out, Omarchy is worth exploring. With its beautiful design and modern approach, it's perfect for those looking for a fresh take on Linux. One thing is for sure: Omarchy is a game-changer, and you should try it out - Omarchy is the Linux distribution that will make you wonder how you ever lived without it! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 cordiverse/cordis is trending — and it deserves your attention. 🔗 https://github.com/cordiverse/cordis 📝 Meta-Framework of Spatiotemporal Composability ────────────────────────────── The Cordis repository on GitHub is an open-source project that focuses on data science and machine learning applications. The purpose of Cordis is to provide a framework for building and deploying scalable data pipelines. Key features of Cordis include modular design, flexible configuration options, and support for various data sources. To use Cordis, users can import the necessary modules and define their data pipelines using a simple and intuitive API. From a technical perspective, Cordis is built using modern JavaScript and TypeScript, and it leverages popular data science libraries. Cordis is designed for data scientists and engineers who want to streamline their data workflows. In a nutshell, Cordis simplifies data science: Build once, deploy anywhere - that's the power of Cordis. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 citrolabs/ego-lite landed on trending. Worth a proper look. 🔗 https://github.com/citrolabs/ego-lite 📝 The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config. ────────────────────────────── Introducing ego lite, a browser designed for parallel work between humans and AI agents. It allows agents to run multiple browser tasks in isolated Spaces, increasing task completion speed and reducing token usage. Key features include a dedicated Space for each agent, multitasking capabilities, and high-quality page snapshots. The ego-browser skill enables any agent to drive the browser, exposing it as a set of in-page JavaScript tools. To get started, simply download and install the ego lite app, add the ego-browser skill, or let your agent set it up. Then, run your first task using the /ego-browser command. Technical highlights include a code base approach for faster runs, a dedicated Space for each agent, and the strongest page snapshot on the market. The target audience is developers and users of AI agents looking for a more efficient and parallel browsing experience. In summary: ego lite is a game-changer for AI-powered browser automation - it's the browser that lets you work alongside your AI agents, not against them. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet HKUDS/CLI-Anything: a gem from today's GitHub trending list. 🔗 https://github.com/HKUDS/CLI-Anything 📝 "CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub:https://clianything.cc/ ────────────────────────────── CLI-Anything is an innovative project that bridges the gap between AI agents and the world's software by making any software agent-ready. The project's primary goal is to create a community-driven hub where users can browse, install, and manage various Command-Line Interfaces (CLIs) for different software applications. Key Features: - CLI-Hub: A centralized registry where users can discover, install, and manage CLIs for various software applications. - One Command Line: A unified interface for interacting with different software applications. - Community-Driven: Users can contribute to the project by creating and sharing their own CLIs. Technical Highlights: - Built using Python and Click. - Uses Pytest for testing and coverage. - Supports multiple output formats, including JSON and human-readable text. The project is suitable for developers, researchers, and power users who want to automate tasks, integrate different software applications, or create custom workflows. With CLI-Anything, users can harness the power of AI agents to interact with a wide range of software applications, from productivity tools to creative software. In a nutshell, CLI-Anything is revolutionizing the way we interact with software by providing a unified, community-driven platform for creating and sharing CLIs - Empowering humans and agents to achieve more, one command line at a time! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: ToolJet/ToolJet — let's break it down. 🔗 https://github.com/ToolJet/ToolJet 📝 ToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀 ────────────────────────────── Introduction to ToolJet: ToolJet is an open-source, AI-native platform for building and deploying internal tools, workflows, and AI agents. The community edition offers a visual builder, drag-and-drop UI, and integrations with databases, APIs, SaaS apps, and object storage. Key Features: - Visual App Builder with 60+ responsive components - Built-in no-code database - Multi-page Apps & Multiplayer Editing - 80+ Data Sources - Flexible Deployment options - Collaboration Tools - Extensibility through plugins and connectors - Code execution for JavaScript and Python - Secure by Design with AES-256-GCM encryption Usage: Get started with ToolJet Cloud or self-host using Docker, Kubernetes, AWS, GCP, Azure, and more. Try the Docker command:

docker run \
  --name tooljet \
  --restart unless-stopped \
  -p 80:80 \
  --platform linux/amd64 \
  -v tooljet_data:/var/lib/postgresql/13/main \
  tooljet/try:ee-lts-latest

Audience: ToolJet is designed for developers, data scientists, and business users looking to build custom internal tools and workflows. One-liner takeaway: ToolJet empowers users to build and deploy custom internal tools and AI agents with ease, streamlining workflows and boosting productivity. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into altic-dev/FluidVoice — fresh off the trending list. 🔗 https://github.com/altic-dev/FluidVoice 📝 Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. A local Wispr Flow alternative. ⭐ helps a ton :) Windows & iOS waitlist open. Linux soon. ────────────────────────────── FluidVoice is an open-source, on-device voice-to-text dictation app for macOS, with AI enhancement. It features multiple speech models, including Nemotron Speech 3.5, Parakeet Flash, and Whisper, allowing users to choose the model that best fits their language and latency needs. Fluid Intelligence, a local AI runtime, powers advanced dictation enhancement, ensuring all data stays on the user's Mac. You can install FluidVoice using Homebrew:

brew install --cask fluidvoice

. The app offers various features, including Command Mode for controlling the Mac by voice, Write Mode for writing or rewriting text in any app, and Live Preview for real-time transcription. Key highlights of FluidVoice include its fast and accurate dictation capabilities, optional AI enhancement via cloud providers or local Fluid Intelligence, and adaptive theming to match the system's light or dark theme. The app is suitable for developers, writers, and anyone looking for a reliable and private dictation experience. In a nutshell, FluidVoice is the ultimate voice-to-text solution for macOS, offering unparalleled speed, accuracy, and privacy - give it a try and experience the future of dictation! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: megadose/holehe — let's break it down. 🔗 https://github.com/megadose/holehe 📝 holehe allows you to check if the mail is used on different sites like twitter, instagram and will retrieve information on sites with the forgotten password function. ────────────────────────────── Holehe is an OSINT tool that efficiently finds registered accounts from emails. It checks if an email is attached to an account on over 120 sites like Twitter, Instagram, and Imgur. The tool retrieves information using the forgotten password function without alerting the target email. It runs on Python 3 and can be installed via PyPI, GitHub, or Docker. Holehe can be run from the CLI or embedded within existing Python applications. For each module, data is returned in a standard dictionary format with details like rateLimit, exists, emailrecovery, and more. It's ideal for security researchers and developers. The tool has a Maltego Transform and is built for educational purposes only under the GNU General Public License v3.0. Get started with Holehe today and uncover hidden accounts - one email at a time! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 github/spec-kit just hit the trending charts — here's why it matters. 🔗 https://github.com/github/spec-kit 📝 💫 Toolkit to help you get started with Spec-Driven Development ────────────────────────────── Spec Kit is an open source toolkit that enables spec-driven development for building high-quality software with any AI coding agent. It provides a ready-to-use, spec-driven process that's endlessly extensible, community-driven, and suitable for entire organizations. The key features of Spec Kit include: - Spec-Driven Development: Flips the script on traditional software development by making specifications executable. - Specify CLI: A command-line interface for managing spec-driven development workflows. - AI Coding Agent Integrations: Supports over 30 AI coding agents, including CLI tools and IDE-based assistants. - Extensions and Presets: Allows for customization through extensions and presets, as well as project-local overrides. To get started with Spec Kit, you can: uv tool install specify-cli --from git+https://github.com/github/spec-kit.git@vX.Y.Z Then, initialize a project with specify init my-project --integration copilot and establish project principles using /speckit.constitution. Spec Kit is designed for developers, organizations, and communities looking to streamline their software development process with AI coding agents. The technical highlights of Spec Kit include its ability to generate executable specifications, create technical implementation plans, and break down tasks for implementation. In a nutshell, Spec Kit revolutionizes software development by making specifications the king, and code its servant - build what you specify, not the other way around. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe