📦 tencent-hunyuan/unirl

UniRL: The Ultimate Unified Reinforcement Learning Framework

Unlock the full potential of your multimodal models with UniRL, a powerful framework designed for unified reinforcement learning across diverse model families. Whether you are working with image and video diffusion models or autoregressive vision-language systems, UniRL streamlines the entire post-training loop. It coordinates sample generation, reward scoring, and policy updates using a composable, layered architecture that makes complex RL experiments manageable. With support for advanced techniques like Flow-DPPO and DRPO, this project provides a consistent way to scale and train high-performing AI. It is time to simplify your research workflow and push your multimodal models further.

🆔 @hackernewsgithubprojects

📦 pardnchiu/agenvoy

Build Your Own Personal AI Agent

Want to make AI actually work for you instead of just chatting? Agenvoy is a powerful productivity infrastructure that turns your computer into a personal agent hub using a single binary. It intelligently routes tasks to the best models like Claude, GPT, or Gemini and lets you teach the agent to build its own tools automatically. If it lacks a specific capability, it finds the right API, creates a script, and saves it for later. Whether you are using Telegram, Discord, or your terminal, this system manages your memory, schedules tasks, and even self-improves its skills whenever an error occurs.

🆔 @hackernewsgithubprojects

📦 junhoyeo/contrabass

Contrabass: The Ultimate Orchestrator for AI Coding Agents

Tired of manually managing your AI coding agents and struggling with fragmented workflows? Meet Contrabass, a powerful project-level orchestrator designed to help you manage work rather than individual agents. Built on a Go and Charm stack, it functions like mission control for your development team by automating issue-driven runs across platforms like Linear and GitHub. It handles everything from workspace isolation and dependency gating to live agent monitoring through its embedded Ziikoo dashboard. With multi-agent coordination, automated recovery, and real-time visibility, Contrabass turns your AI tools into a truly cohesive system. Start orchestrating your coding agents more effectively today.

🆔 @hackernewsgithubprojects

📦 valkor-ai/loom

Stop Coding Demos: Turn AI Agents into Pro Delivery Systems with Loom

Are your AI coding agents stuck building one-off demos instead of production-ready software? Loom is an open-source delivery harness designed to solve this by turning agents like Claude Code or Codex into repeatable, reliable systems. Instead of losing context or dealing with goal drift, Loom forces a structured loop of planning, execution, verification, and repair. It persists your project state, keeps requirements aligned, and tracks backend readiness so you can actually finish what you start. Stop wasting tokens on partial progress and start shipping reliable code today by giving your agents the professional delivery structure they need.

📰 https://news.ycombinator.com/item?id=48472991

🆔 @hackernewsgithubprojects

📦 elvisun/newsjack

Turn Your AI Agent Into a Full PR Team

Want to supercharge your AI agent for public relations? This project provides a collection of open-source skills designed to turn your agent into a high-functioning PR team. It solves the problem of manual PR work by allowing you to automate tasks like monitoring industry news, tracking competitors, verifying story freshness, and generating targeted pitch angles. Whether you are a founder, a marketer, or an agency lead, these tools help you surface opportunities and refine your messaging with precision. Simply install the tools to your agent's runtime to start building your media strategy and elevate your brand presence today.

📰 https://news.ycombinator.com/item?id=48461894

🆔 @hackernewsgithubprojects

📦 davila7/claude-code-templates

Supercharge Your Claude Code Workflow

Are you looking to take your AI-powered development to the next level? This repository offers a powerful command line tool designed to configure and monitor your Claude Code experience with ease. It provides an extensive library of specialized templates and agents, ranging from AI ethics advisors and database architects to full stack developers and security auditors. By leveraging these structured components, you can streamline your tasks, improve project consistency, and get the most out of your coding assistant. Dive into these templates to unlock a more efficient and organized development workflow starting today.

🆔 @hackernewsgithubprojects

📦 rorkai/app-store-connect-cli

Automate App Store Connect Like a Pro

Are you tired of manually navigating the App Store Connect website for every single release? Meet this fast, scriptable command-line tool designed to handle your entire iOS, macOS, tvOS, and visionOS workflow directly from your terminal. Whether you need to manage TestFlight builds, update metadata, handle app submissions, or automate code signing, this project removes the headache of interactive prompts with a clean, JSON-first approach. It is built in Go and designed for seamless integration into your CI/CD pipelines. Take control of your release process today and spend less time clicking through menus and more time building.

🆔 @hackernewsgithubprojects

📦 junhoyeo/tokscale

Stop Guessing Your AI Coding Costs with Tokscale

Are you curious about exactly how many tokens your AI coding assistants are consuming? Meet Tokscale, a powerful command-line tool designed to track, visualize, and analyze your AI usage across dozens of platforms like Claude Code, Cursor, and Gemini. By leveraging a high-performance Rust core, it provides deep insights into your spending and token activity through an interactive terminal dashboard. You can explore detailed statistics, view contribution graphs, and even sync data for a global leaderboard. It is the perfect way to stay in control of your developer productivity. Start tracking your AI energy today and level up.

🆔 @hackernewsgithubprojects

📦 m5stack/stackchan

Build Your Own AI Robot Companion with StackChan

Have you ever wanted to build your own expressive AI robot companion? Meet StackChan, an open-source project from M5Stack that brings a adorable, desktop-sized robot to life. This repository provides everything you need, including firmware for the ESP32-S3 powered controller and a full-featured Flutter mobile app for both iOS and Android. With capabilities like real-time AI conversation, facial expression rendering, and customizable dance choreography, it is a powerful platform for hobbyists. Whether you are coding in Arduino or building mobile interfaces, StackChan offers a vibrant community-driven ecosystem to explore. Grab your hardware and start building your custom robot today!

🆔 @hackernewsgithubprojects

📦 priyanshu-1622/skiff

Stop Storing SSH Credentials in Cloud Apps - Meet Skiff

Are you tired of paying for subscription-based SSH managers just to keep your server credentials organized? Meet Skiff, an open-source, self-hosted alternative that puts you back in total control. It lets you store hosts, manage them in folders, and connect directly through an in-browser terminal without any cloud dependency. Everything is encrypted at rest using industry-standard security, and you can even set up a team mode to share vaults with recorded audit logs. It is built with a focus on privacy, so you own your data entirely. Stop compromising your security and start self-hosting your SSH inventory today.

🆔 @hackernewsgithubprojects

📦 davide-desio-eleva/kirograph

Supercharge Your AI Coding with KiroGraph

Are your AI coding tools wasting time and context on redundant searches? Meet KiroGraph, a powerful semantic knowledge graph built specifically for Kiro. By using Tree-sitter to parse your codebase into a local SQLite database, it gives your AI instant access to symbol relationships, call graphs, and type hierarchies without constant file scanning. It solves the problem of bloated tool calls, keeping everything 100% local and private. With built-in features like impact analysis, security vulnerability tracking, and architecture insights, you get faster, more accurate responses on complex tasks. Install it today to see how much more efficient your development workflow becomes.

📰 https://news.ycombinator.com/item?id=48220335

🆔 @hackernewsgithubprojects

📦 libertywing/flashmemory-deepseek-v4

Slash Your LLM Memory Costs with FlashMemory

Struggling with the massive memory demands of long-context AI models? Meet the FlashMemory Retriever, a lightweight tool designed to sparsify the DeepSeek-V4 compressed KV-cache. This project solves the problem of heavy GPU memory usage by predicting exactly which cache chunks are necessary for upcoming tokens. By keeping only the most relevant ten to fifteen percent of data on-device and offloading the rest, it maintains high-performance reasoning while drastically reducing memory overhead. It is a brilliant way to optimize resource efficiency without sacrificing accuracy, giving you a smarter, leaner approach to handling ultra-long sequences in your own AI workflows.

🆔 @hackernewsgithubprojects

📦 genalyu/3spo

3SPO: A Breakthrough for Fine-Grained AI Training

Are you struggling with sparse rewards when training large language models? Meet 3SPO, a powerful framework designed to bridge that gap. By converting simple trajectory outcomes into detailed, step-level supervision, 3SPO uses a dynamic state-score mechanism to prioritize challenging states and guide model learning more effectively. It helps you avoid wasting resources on overly difficult tasks while maximizing the impact of every training step. With built-in support for adaptive rollouts and compatibility with popular engines like vLLM and SGLang, 3SPO gives you the tools to refine complex model performance. Try it out to take your reinforcement learning experiments to the next level.

🆔 @hackernewsgithubprojects

📦 qinghonglin/data2story-skill

Turn Any Dataset Into a Verifiable Story with This AI Agent

Ever wanted to turn raw data into a compelling, evidence-backed story without doing all the heavy lifting? Meet this clever data journalist agent that acts like a newsroom in a box. By orchestrating a pipeline of seven specialized roles, including a detective, analyst, designer, and programmer, it researches context, profiles data, and builds a fully traceable multimodal article. Every sentence produced is verifiable, meaning you can trace findings directly back to their source. Whether you are creating charts, videos, or music, this tool helps you build reproducible, professional-grade stories automatically. Take your data storytelling to the next level.

🆔 @hackernewsgithubprojects

📦 haodong-lei-ray/pathspec

Speed Up Text-to-Image Generation with PathRelax

Struggling with slow auto-regressive text-to-image generation? Meet PathRelax, a powerful repository focused on accelerating this process through Parallel-Path Relaxed Speculative Jacobi Decoding. This project provides researchers and developers with a suite of benchmark scripts to evaluate performance across popular datasets like MSCOCO and PartiPrompts. By leveraging specific techniques like static tree structures for draft token generation, it helps optimize efficiency in complex generative tasks. If you are looking to push the boundaries of model inference speed, these evaluation tools offer a practical way to test and refine your configurations for high-quality image output.

🆔 @hackernewsgithubprojects

📦 alibaba-flyai/flyai-skill

Plan Your Next Trip Directly From Your Terminal

Stop switching between travel sites and your coding environment. FlyAI is a powerful skill that brings real-time travel search directly into AI agents like Claude Code. Whether you need to compare flight prices, find hotels near specific attractions, or search for train tickets and concerts, this tool handles it all using natural language. It connects your terminal to the vast travel inventory of Fliggy, providing structured data you can easily filter or analyze. Stop juggling browser tabs for your next vacation plan and let your AI assistant handle the logistics for you starting today.

🆔 @hackernewsgithubprojects

📦 zebbern/claude-code-guide

Master Claude Code with 100+ Specialized Agents

Stop struggling with generic AI prompts and start working like a pro using the Claude Code Guide. This comprehensive resource offers a massive library of over one hundred specialized workspace agents designed to handle specific technical tasks. Whether you need a backend developer, a security auditor, or a test architect, these pre-configured agents provide the expertise you need directly within your coding environment. By leveraging structured workflows and expert skills for everything from database optimization to accessibility testing, you can significantly level up your development speed and code quality. Dive into this guide to unlock your true power-user potential.

🆔 @hackernewsgithubprojects

📦 george-ling3/blue

Stop Wasting Compute: Smarter AI Driving with BLUE

Are your vision-language models for autonomous driving working too hard? Often, these models generate unnecessary language reasoning that slows down performance and can even cause errors. The BLUE repository tackles this by introducing a compact zero-point-one-one million parameter gate that intelligently decides frame by frame when language generation is actually useful. By predicting driving actions only when needed, this approach boosts performance while significantly reducing inference latency. If you are building autonomous systems and want more efficiency without sacrificing accuracy, this project offers a smarter way to handle complex reasoning tasks in real time.

🆔 @hackernewsgithubprojects

📦 sumanth077/ai-engineering-toolkit

The Ultimate Toolkit for AI Engineers

Are you struggling to navigate the overwhelming landscape of AI development tools? This repository is a powerhouse for AI engineers, acting as a massive curated directory of over one hundred essential libraries and frameworks designed for building Large Language Model applications. Whether you need vector databases like Pinecone for data retrieval, agent frameworks such as AutoGen for autonomous workflows, or fine-tuning tools like Unsloth to optimize performance, this collection has it all. It saves you valuable time by centralizing production-ready resources in one place, helping you build, deploy, and scale smarter AI systems today.

🆔 @hackernewsgithubprojects

📦 noopapp/noop

Take Full Control of Your WHOOP Data Offline

Tired of locked-in health data and subscription fatigue? Meet NOOP, a powerful, local-first companion for your WHOOP strap that lets you reclaim your biometric stream. Instead of relying on the cloud, NOOP pairs directly with your device over Bluetooth to store heart rate, recovery, and sleep data securely on your own hardware using SQLite. You can even import your existing history for a complete, private dashboard with transparent, on-device analytics and helpful automations. It is completely account-free, subscription-free, and open for you to explore. Own your metrics and keep your health data truly yours by running it all locally today.

📰 https://news.ycombinator.com/item?id=48476432

🆔 @hackernewsgithubprojects

📦 thejudge26/c-asterisk-alpha

Is This The Secret To Super Fast Machine Learning?

Imagine getting the simplicity of Python with the raw power of a systems language. Meet C-Star, a custom programming language designed to bridge that gap by compiling directly to native machine code using LLVM. This project solves the problem of Python's slow execution speeds in data-heavy tasks by utilizing native I/O bypasses and a statically typed architecture. In rigorous benchmarks, C-Star outperformed Python by nearly one hundred times on complex neural network tasks, matching the performance of C++ while keeping the code readable. It is a brilliant example of how choosing the right compiler infrastructure changes everything.

🆔 @hackernewsgithubprojects