📦 traceopt-ai/traceml

Stop Guessing: Debug PyTorch Training Performance with TraceML

Is your PyTorch training running slower than expected? Meet TraceML, a lightweight diagnostic tool designed to help you pinpoint performance bottlenecks without the overhead of heavy profilers. By wrapping your training step, TraceML monitors critical metrics like input latency, memory creep, and distributed rank imbalances. It provides a clear, actionable summary at the end of every run, identifying whether your issues stem from a slow dataloader, GPU wait times, or infrastructure changes. With under two percent performance overhead, it is the perfect first step to diagnose training issues and optimize your deep learning workflows for maximum efficiency.

🆔 @hackernewsgithubprojects

📦 funnywolf/agentic-soc-platform

Stop Alert Fatigue: The Agentic SOC Platform Explained

Are you drowning in endless security alerts? Meet the Agentic SOC Platform, an open-source, AI-driven solution designed to clear the noise from your security operations. By using an agentic framework to aggregate logs and correlate threats, it reduces millions of alerts into a handful of actionable cases. It features automated investigation reports, one-click playbooks, and unified access across different SIEM systems. Because it is built with Python and supports private, on-premise deployment, your sensitive data stays secure. Transform your workflow from constant manual digging to smart, AI-assisted decision making and let your team focus on real threats.

🆔 @hackernewsgithubprojects

📦 rapiercraftstudios/forgedock

Automate Your Dev Pipeline with ForgeDock

Stop letting AI agents forget your project context between coding sessions. ForgeDock acts as an autonomous development pipeline that turns GitHub into a persistent knowledge graph for your AI agents. By using structured annotations, it allows agents to pick up exactly where they left off, preventing them from repeating the same mistakes. From investigating bugs to building fixes and conducting domain-specific reviews, ForgeDock orchestrates the full lifecycle for you. It is a powerful way to bring institutional memory to your development process, ensuring your AI stays smart and your workflow remains fast. Start automating your codebase today.

🆔 @hackernewsgithubprojects

📦 cvlab-kaist/geometric-action-model

Geometric Action Model: The Future of Robot Policy Learning

Imagine giving robots a deeper understanding of how their physical movements interact with the world around them. This repository serves as the official home for the Geometric Action Model, a new approach designed to improve robot policy learning. While the project is currently in its early stages with code arriving soon, it represents a significant collaborative effort between researchers at KAIST and ETH Zurich to refine how machines interpret spatial relationships. By focusing on geometry, this research aims to make robotic actions more precise and adaptable. Keep an eye on this space as the implementation unfolds and transforms robotic intelligence.

🆔 @hackernewsgithubprojects

📦 patrickjaja/claude-desktop-bin

Get Claude Desktop on Linux Today

Want to run Claude Desktop on your Linux machine but thought you were out of luck? This project brings the full Claude Desktop experience to Linux, featuring automated updates and seamless support for advanced capabilities like Computer Use, agentic workspaces, and custom themes. It patches platform limitations to let you use powerful tools for desktop automation, window management, and integrated coding right on your preferred Linux distribution. With support for Arch, Debian, Fedora, and Nix, it is easier than ever to boost your productivity. Give your Linux desktop the AI assistant it deserves and start building faster today.

🆔 @hackernewsgithubprojects

📦 stevesolun/ctx

Supercharge Your AI Agents with This Massive Knowledge Graph

Ever wonder how to make your AI agents and coding tools smarter and more capable? This repository is a powerhouse for anyone working with custom LLMs and Claude Code, offering a staggering library of over ninety thousand skills, hundreds of agents, and thousands of Model Context Protocol recommendations. It functions as a massive, structured knowledge graph designed to help you discover, manage, and install specialized tools to enhance your AI workflows. Whether you need better architectural patterns or precise code validation, this project provides the registry and framework to level up your automation. Start building more effective AI systems today.

📰 https://news.ycombinator.com/item?id=48559559

🆔 @hackernewsgithubprojects

📦 digital-process-tools/claude-remember

Give Claude Code Permanent Memory

Tired of starting from scratch every time you open Claude Code? It forgets your past work, team conventions, and previous mistakes, forcing you to re-explain everything. Claude Remember solves this by acting as persistent memory for your sessions. It automatically saves your work, compresses it into concise summaries using Haiku, and reloads that context whenever you start a new session. Your agent finally develops real continuity, remembering what it learned and what worked before. Stop wasting time on repetitive prompts and let your AI assistant actually remember your project history. Get started and keep your project context alive.

🆔 @hackernewsgithubprojects

📦 zai-org/glm-5

Meet GLM-5: The New Powerhouse for Agentic AI

Are you ready to elevate your AI development? The GLM-5 repository introduces a flagship series of open-source models specifically built for complex systems engineering and long-horizon agentic tasks. These models feature a stable one-million-token context and advanced architecture, such as IndexShare, to boost coding performance while managing latency. Whether you are running long-term simulations or building intricate applications, GLM-5 provides the precision needed for modern agentic workflows. With support for major deployment frameworks, it is time to integrate this powerful intelligence into your own projects and experience the future of AI engineering for yourself.

🆔 @hackernewsgithubprojects

📦 higress-group/himarket

Build Your Own Private AI Marketplace with HiMarket

Are you struggling to manage scattered AI models, agents, and tools across your organization? Meet HiMarket, an enterprise-level platform that transforms how teams share and govern AI assets. Instead of dealing with fragmented APIs, HiMarket lets you package, manage, and publish models, agent skills, and server tools as standardized products. It provides a unified hub for developers to discover and use these resources while giving administrators full control over security, observability, and billing. With built-in features like HiChat and secure online programming environments, HiMarket turns your internal AI resources into a seamless, professional ecosystem. Simplify your enterprise AI strategy today.

🆔 @hackernewsgithubprojects

📦 nvlabs/soma-x

Stop Managing Incompatible Human Body Models with SOMA

Tired of dealing with incompatible human body models like SMPL, SMPL-X, and Anny? Meet SOMA, a revolutionary project that unifies these diverse standards into one single, shared topology. Instead of building custom adapters for every new model, SOMA acts as a universal pivot, letting you animate different identities using a unified pipeline. It is fully GPU-accelerated and provides end-to-end differentiable processing, making it a game-changer for human reconstruction and simulation. Whether you are working on digital humans or physical AI, SOMA simplifies your workflow by letting you mix and match data instantly. Try SOMA today and streamline your 3D animation projects.

🆔 @hackernewsgithubprojects

📦 tigerless-labs/cost-xray

Stop Overpaying for AI: Audit Your Claude Code & Codex API Spend

Ever wonder what your AI coding agent is actually sending to the cloud and how much those hidden prompts are really costing you? Most tools only show you the final bill, but cost-xray gives you total transparency. By acting as a local traffic capture, it records exactly what Claude Code or Codex sends to the API, including system prompts and tool schemas. It breaks down costs per turn, revealing which specific parts of your request are eating up your budget. Stop guessing why your costs are spiking and start optimizing your workflow today. Grab control of your AI spending with this powerful visibility tool.

📰 https://news.ycombinator.com/item?id=48480921

🆔 @hackernewsgithubprojects

📦 greensheep01201/claw-empire

Build Your Own AI Agent Empire

Ever wanted to play CEO to a team of artificial intelligence assistants? This local-first simulator turns your AI coding tools into a virtual company of autonomous agents. By integrating CLI, OAuth, and API-connected providers like Claude Code and Gemini, you can orchestrate a full office environment where agents collaborate, attend meetings, and tackle complex tasks in isolated git worktrees. It features a charming pixel-art interface, a comprehensive Kanban board for project management, and a massive library of over six hundred skills. It is an engaging way to visualize and manage your autonomous workflow, so start building your empire today.

🆔 @hackernewsgithubprojects

📦 zhaoxuya520/reverse-skill

Supercharge Your Security Workflow with AI Agents

Are you struggling to manage complex security research or reverse engineering tasks with your AI coding assistant? This repository offers a powerful skill router pack designed to transform how AI agents handle cybersecurity workflows. It automatically classifies tasks, guides the AI through specialized methodologies, and manages on-demand toolchain bootstrapping. Whether you are dealing with mobile app reversing, binary analysis, or CTF challenges, this system ensures your AI uses the right tools and strategies every time. By consolidating workflows into a portable asset, it bridges the gap between general AI capabilities and expert security execution. Elevate your technical efficiency and let automation handle the heavy lifting.

🆔 @hackernewsgithubprojects

📦 sermakarevich/sddw

Stop Prompting, Start Engineering: Meet SDDW

Are you tired of AI coding agents losing context and drifting off track? Standard prompting often fails for complex projects, but the Spec Driven Development Workflow changes everything. Instead of messy, open-ended chats, this framework turns requirements into structured, version-controlled specifications. By guiding you through a rigorous process of design, task breakdown, and verified implementation, it keeps your code architecture-aligned and error-free. You gain a professional-grade workflow that remains persistent across sessions, ensuring every task is purposeful. Take control of your AI collaboration and transform how you build software by grounding every single line of code in clear, reviewable documentation.

📰 https://news.ycombinator.com/item?id=48183043

🆔 @hackernewsgithubprojects

📦 jacob-bd/notebooklm-mcp-cli

Take Control of NotebookLM with this CLI & MCP Server

Want to supercharge your research workflows? This project provides programmatic access to Google NotebookLM, letting you interact with your notebooks directly from your terminal or through AI assistants. You can automate tasks like creating new notebooks, adding web or drive sources, and even triggering audio overview generation, all using simple commands. By acting as an MCP server, it allows tools like Claude or Cursor to tap into your NotebookLM data naturally. Whether you need to sync sources, run batch operations, or just streamline your study habits, this tool bridges the gap between your AI agents and your notes.

🆔 @hackernewsgithubprojects

📦 marckrenn/claude-code-changelog

Track Every Claude Code Update Automatically

Ever wonder how Claude Code evolves behind the scenes? This repository is an unofficial, community-driven archive that tracks the progression of system prompts, feature flags, and metadata across every single Claude Code release. It solves the difficulty of manual tracking by providing a structured, searchable history of how the tool changes over time. You can compare different versions to see exactly how instructions or behaviors shift between updates. It is a fantastic resource for anyone wanting to conduct deep research on prompt engineering or AI tool development. Dive in today to see exactly how these intelligent systems grow.

🆔 @hackernewsgithubprojects

📦 mistertea/eternalterminal

Never Lose Your Terminal Session Again with Eternal Terminal

Are you tired of losing your work when your network connection drops? Eternal Terminal is a powerful, secure remote shell that solves this by automatically reconnecting without ever interrupting your active session. It acts like a persistent bridge, maintaining your terminal state even if your internet cuts out or you switch networks. By using SSH for encrypted handshaking and a dedicated server process to manage your terminal, it ensures your command-line tasks stay active in the background. It is the perfect tool for developers who need reliable, continuous access to remote systems. Stop worrying about disconnects and keep your productivity flowing today.

🆔 @hackernewsgithubprojects

📦 vmvlab/medical_embodied_ai_paper_list

The Future of Medicine: Embodied AI Explained

Ever wonder how artificial intelligence might physically transform our hospitals? While foundation models are smart, they often struggle to interact with the real world. This project repository offers a deep dive into the emerging field of Medical Embodied AI. It provides a systematic survey of how agents can integrate perception, decision-making, and action to handle clinical tasks. From recognizing surgical instruments to automating complex workflows, this research explores the next generation of healthcare technology. It is a fantastic resource for understanding the technical roadmap and challenges ahead. Dive into this paper list to see how AI is becoming truly embodied.

🆔 @hackernewsgithubprojects

📦 yaolinwen/domoo

Solving Complex Optimization Challenges Offline with DOMOO

Struggling to find the right balance between conflicting design goals when you only have static, offline data? Meet DOMOO, a research framework presented at ICML 2026 designed to master multi-objective optimization without live feedback. It tackles the common issue of out-of-distribution errors by combining energy-based risk control with a smart nested learning strategy. By jointly training preference models and Pareto sets, it effectively navigates complex design spaces while maintaining high diversity. Whether you are working on neural architecture search or engineering design, this tool helps you find reliable, high-quality solutions. Give your offline optimization models a serious upgrade today.

🆔 @hackernewsgithubprojects

📦 cslsolow/seerepo

Stop Wasting Tokens! Boost Your AI Coding Agents

Are you tired of your AI coding agents burning through tokens just trying to understand a new codebase? Meet SeeRepo, a clever framework designed to make agents smarter and faster. Instead of forcing agents to hunt through files using repetitive shell commands, SeeRepo provides a pre-built structural graph of the entire repository. By mapping out imports, function calls, and class hierarchies, it gives the agent a clear roadmap of how the code connects. This simple change helps agents resolve issues more efficiently without sacrificing accuracy. Dive into the world of graph-augmented agents today and streamline your development workflow.

🆔 @hackernewsgithubprojects