📦 alexknowshtml/claude-skills

Supercharge Your AI Workflow With Claude Skills

Stop wasting time on repetitive tasks and transform your AI workflow with this clever collection of specialized slash commands for Claude Code. This repository provides battle-tested, reusable prompts designed to handle professional development challenges, like managing session pauses, conducting retrospectives, or converting markdown into beautifully styled HTML pages. By simply dropping these pre-built commands into your project, you gain a powerful, structured way to interact with your AI assistant. Stop manual work, start leveraging these streamlined automations, and take full control of your coding sessions today with these simple, highly effective productivity boosters.

🆔 @hackernewsgithubprojects

📦 agent0ai/dox

Stop AI Drift with DOX

Are your AI agents making messy, unpredictable changes to your code? Meet DOX, a clever framework that keeps your projects organized by using a hierarchy of markdown files. Instead of guessing, agents read these specific instruction files before every edit, ensuring they follow your rules exactly. You simply add a markdown file to your project, and the agent builds a tree of local guidelines that keep your code clean and consistent. It prevents drift by requiring agents to update documentation whenever they make meaningful changes. Use DOX to give your AI clear, binding contracts and smarter project context today.

🆔 @hackernewsgithubprojects

📦 human-agent-society/coral

Build Autonomous AI Teams with CORAL

Ever wanted to see AI agents collaborate and evolve their own problem-solving skills? Meet CORAL, a powerful infrastructure designed for autonomous multi-agent research. Instead of working alone, CORAL lets you deploy teams of AI agents, like Claude Code or Cursor, to run experiments in parallel using isolated git worktrees. The system manages shared state, handles evaluation via a grader daemon, and even triggers periodic heartbeats to keep your agents focused and improving. It is built to turn research tasks into a self-evolving loop, perfect for complex discovery. Ready to scale your autonomous research? Check out this infrastructure and start building today.

🆔 @hackernewsgithubprojects

📦 nv-tlabs/gamma-world

Gamma-World: The Future of Multi-Agent Simulation

Ever wonder how to simulate complex, multi-agent worlds where every character stays in sync? Introducing Gamma-World, an innovative generative model designed to roll out shared environments for multiple independent agents. While most models struggle with single-agent settings, Gamma-World uses unique Simplex Rotary Agent Encoding to keep agents distinct yet permutation-equivalent, allowing it to scale from two players to four without extra training. With efficient Sparse Hub Attention to handle interactions and a distilled student model for smooth 24 frames per second streaming, this project brings us one step closer to truly interactive, scalable, and intelligent virtual simulations.

🆔 @hackernewsgithubprojects

📦 yennning/awesome-code-as-agent-harness-papers

The Ultimate Resource for AI Code Agent Research

Are you diving into the cutting-edge world of AI code agents? This GitHub repository serves as a meticulously curated collection of research papers and academic resources focused on code-based agent harnesses. It functions as a centralized knowledge hub for developers and researchers to track key developments in how AI interacts with code-driven environments. By organizing complex literature into structured categories like mechanisms and scaling, it helps you navigate the rapidly evolving landscape of software-participating agents. Whether you are performing a literature review or building your own systems, this repository offers a clear, organized, and community-driven path to master this technology.

🆔 @hackernewsgithubprojects

📦 quarqlabs/argus

Build Smarter AI Agents with Argus

Most AI agents struggle to actually remember past interactions, but Argus is changing that. It is a local, memory-first cognitive runtime designed for AI agents that require precise recall, temporal reasoning, and reliable quantitative data. Instead of simple vector search, Argus uses a sophisticated hybrid retrieval system to separate semantic facts from episodic history and behavioral rules. It actively solves common AI failures, such as misattributing numbers or confusing events, by using self-correcting fallback logic. Whether you are building complex task agents or just need better long-term memory for your projects, Argus offers a disciplined framework for truly intelligent interaction.

🆔 @hackernewsgithubprojects

📦 deusyu/translate-book

Translate Entire Books Automatically with Claude Code

Ever wanted to translate an entire book but got frustrated by AI context limits or inconsistent terminology? This project is a powerful skill for the Claude Code CLI that automates the translation of PDF, DOCX, and EPUB files into any language. It breaks your book into manageable chunks, utilizing parallel subagents to translate them concurrently while maintaining perfect term consistency through a smart, evolving glossary. It handles everything from format conversion to final output generation, including support for EPUB, PDF, and DOCX. It is the perfect tool for your next literary project. Give it a try and translate effortlessly.

🆔 @hackernewsgithubprojects

📦 rizal72/true-mem

Stop Repeating Yourself: True-Mem for OpenCode

Tired of reminding your AI assistant about your project preferences every single time? True-Mem is a smart memory plugin for OpenCode that finally fixes this. Instead of a simple database, it uses cognitive psychology to manage your memories like a human mind. It automatically classifies information—storing permanent preferences and project decisions while letting temporary details fade away. With its advanced filtering, it ignores noise like questions or AI meta-talk, keeping only what truly matters. Stop the cycle of repeating yourself and let your AI learn your workflow for good, making every session feel like a seamless continuation of your progress.

🆔 @hackernewsgithubprojects

📦 workos/case

Build More Reliable AI Pull Requests

Tired of AI-generated code that fails in production? Meet Case, a specialized reliability layer designed to make agent-authored pull requests consistent, reviewable, and self-improving. Unlike generic agent platforms, Case focuses on a structured pipeline where humans provide the steering while agents execute the implementation. It uses a series of evidence gates—like automated test verification and manual review—to ensure that every change meets your specific quality standards. By recording retrospectives and refining playbooks, Case turns recurring failures into permanent guardrails, ultimately making your development process more predictable. Start using Case today to transform how your agents contribute code.

🆔 @hackernewsgithubprojects

📦 pixijs/pixijs-skills

Master PixiJS with Official AI Coding Skills

Want to build high-performance 2D web graphics faster? This repository is the official collection of AI skills for PixiJS version eight, specifically designed to train coding agents to write professional-grade code. Whether you are setting up your first application, managing complex scene graphs with containers and sprites, or optimizing performance, these structured skill modules guide AI to use the library correctly. From handling WebGL and WebGPU rendering to advanced tasks like custom shaders, these skills ensure your AI assistant follows the latest patterns, making it an essential companion for building smooth, interactive projects on the web.

🆔 @hackernewsgithubprojects

📦 chenhg5/agencycli

Build Autonomous AI Teams with agencycli

Want to build an autonomous AI team that runs while you sleep? Meet agencycli, a lightweight tool that lets you define your organization using simple Markdown and YAML. Instead of writing complex code, you set up teams, roles, and project blueprints that your agents follow. These agents communicate through an inbox, delegate tasks, and even wake up on a schedule to get work done. It works with tools like Claude Code, Gemini, and Cursor, running them inside secure Docker containers. It is the perfect way to turn your ideas into a self-managing AI workforce, so start building your digital agency today.

🆔 @hackernewsgithubprojects

📦 thudm/indexcache

Speed Up Sparse Attention Models with IndexCache

Are you struggling with slow performance in long-context models using DeepSeek Sparse Attention? IndexCache is a game-changing solution that drastically accelerates inference by cutting out redundant computations. By discovering that adjacent layers share nearly all their selected tokens, this project introduces a clever way to reuse indices instead of calculating them at every single layer. This simple yet effective patch for SGLang and vLLM eliminates up to seventy-five percent of indexer work, delivering massive speedups for your prefill and decode tasks without sacrificing quality. Unlock faster, more efficient AI performance today with this powerful optimization technique.

📰 https://news.ycombinator.com/item?id=48569165

🆔 @hackernewsgithubprojects

📦 vakovalskii/codbash

Stop Losing Your AI Coding Sessions!

Are you tired of losing track of your AI coding sessions scattered across different tools and folders? Meet Codbash, a powerful browser-based control room designed to bring all your AI coding history into one organized place. Whether you are using Claude Code, Cursor, Codex, or other popular agents, this dashboard lets you search, resume, and manage your workflows with ease. You can view session replays, monitor live statuses, and even calculate costs based on real token usage. With its intuitive interface, you can finally stop digging through logs and start coding more efficiently. Simplify your AI development workflow today.

🆔 @hackernewsgithubprojects

📦 bvisible/mcp-ssh-manager

Control Your Servers with AI: MCP SSH Manager

Are you tired of manually jumping between servers to manage your infrastructure? Meet the MCP SSH Manager, a powerful tool designed to bridge the gap between your AI assistant and your remote machines. By using the Model Context Protocol, this software empowers Claude Code and OpenAI Codex to securely execute commands, transfer files, and monitor health across all your servers. With thirty-seven built-in tools covering everything from automated backups to database management, it turns complex DevOps tasks into simple natural language requests. Supercharge your remote management workflow and let your AI handle the heavy lifting starting today.

🆔 @hackernewsgithubprojects

📦 greensock/gsap-skills

Master GSAP Animations with AI: Official Skills for Developers

Struggling to get your web animations just right? The official GSAP skills repository is a game changer for developers using AI coding agents. It provides a curated collection of specialized instructions that teach AI exactly how to use the GreenSock Animation Platform correctly. From core tweening methods and performance optimization to framework-specific integration for React, Vue, and Svelte, these skills ensure your generated code follows industry best practices. Stop wasting time debugging animation patterns and let these precise guidelines handle the complexity for you. Integrate these skills today to streamline your workflow and start building smoother, professional-grade animations effortlessly.

🆔 @hackernewsgithubprojects

📦 caramaschihg/awesome-ai-agents-2026

The Ultimate Guide to AI Agents in 2026

Are you feeling overwhelmed by the endless wave of new artificial intelligence tools? This repository is your ultimate survival guide, acting as a massive, monthly-updated directory that organizes over three hundred and forty of the best AI agents, frameworks, and productivity tools into twenty clear categories. Whether you need autonomous coding assistants like Devin, multi-agent frameworks to scale your workflow, or creative tools for media generation, this project cuts through the noise. It helps you quickly identify the right technology for your specific needs, making it an essential resource for anyone looking to master the agentic future of software.

🆔 @hackernewsgithubprojects

📦 aaronsb/obsidian-mcp-plugin

Give Your AI Vault-Level Intelligence with Obsidian MCP

Unlock the full potential of your knowledge base by giving AI direct agency over your Obsidian notes. This repository provides a high-performance server that connects your local vault to AI assistants using the open Model Context Protocol. Instead of seeing isolated files, your AI can now traverse your knowledge graph, perform semantic searches, and execute complex file operations like splitting or merging notes. It seamlessly bridges the gap between your private data and powerful AI tools, enabling you to synthesize ideas and explore connections effortlessly. It is a game changer for turning your notes into a truly intelligent research assistant.

🆔 @hackernewsgithubprojects

📦 modelscope/twinkle

Supercharge Your Model Training with Twinkle

Struggling to get your AI models performing at their peak? Meet Twinkle, a comprehensive training workbench designed to help your models shine. This project provides a powerful infrastructure for fine-tuning and optimizing large language models, offering modular components like custom loss functions, advanced samplers, and specialized checkpoint engines. Whether you are dealing with complex data loading or need robust NPU support, it streamlines the training process through a flexible, scalable architecture. It is essentially a professional-grade toolkit that simplifies sophisticated training workflows, allowing you to focus on achieving better results. Dive into this repository to elevate your model development journey today.

🆔 @hackernewsgithubprojects

📦 ballred/obsidian-claude-pkm

Stop Failing Your Goals: Obsidian + Claude AI Accountability

Struggling to keep your goals and daily tasks in sync? This powerful starter kit transforms your Obsidian vault into a high-performance accountability system using Claude Code. By connecting your three-year vision directly to your daily actions, it uses AI-powered agents and slash commands to ensure nothing ever falls through the cracks. Whether you are automating weekly reviews, tracking project progress, or aligning daily habits with long-term milestones, this system keeps you focused and moving forward. Stop guessing where your time goes and start building a workflow that keeps you accountable to your own success starting today.

🆔 @hackernewsgithubprojects

📦 guria/nehir

Take Control of Your Desktop with Nehir

Ever wish your Mac worked more like a professional tiling window manager? Meet Nehir, a scrolling tiling window manager for macOS that transforms how you organize your digital workspace. Inspired by the Niri layout paradigm, it automatically arranges your windows into columns that flow horizontally across your screen. With features like configurable colored window borders, per-monitor status bars, and powerful keyboard-driven navigation, it is designed to keep your workflow efficient and fluid. Whether you are using app rules or custom hotkeys, Nehir gives you total control over your screen real estate. Level up your productivity and streamline your desktop flow today.

🆔 @hackernewsgithubprojects

📦 codehamr/codehamr

Meet the Minimalist Coding Agent for Your Terminal

Are you tired of complex coding tools that clutter your workflow? Meet a minimal, local-first coding agent designed specifically for your terminal. It prioritizes simplicity by avoiding unnecessary features, focusing instead on a streamlined loop that calls tools like bash, file readers, and editors to get the job done efficiently. Built to work with local models or OpenAI-compatible endpoints, it lets you maintain full control over your context window. By automating tasks directly in your project environment, it ensures your code stays clean and manageable. Experience a lighter way to code and let your terminal do the heavy lifting.

🆔 @hackernewsgithubprojects