📦 emilycodes-cmd/claude-code-ollama-local

Claude Code Ollama Local

claude-code-ollama-local is the Windows setup helper that lets you run Anthropic's terminal assistant completely offline without paying for an API key. Instead of sending your code to external servers, this clever configuration redirects everything to your own machine using Ollama. It bundles a simple launcher script to swap the default cloud connection with lightweight, local AI models like Qwen. It even includes handy troubleshooting tips for forcing CPU mode if your graphics card throws a fit. It is the perfect way to get smart terminal help locally, keeping your code private and your wallet happy.

🆔 @hackernewsgithubprojects

📦 penligent/ai2pentesttool

ai2pentesttool

Setting up a security testing lab can be a massive headache of broken dependencies and manual package troubleshooting, but ai2pentesttool fixes this by using a smart AI agent to configure and install your entire security suite in a single click. Instead of blindly running shell scripts, this tool uses GPT-4 to analyze your specific operating system, generate a custom installation plan for fifteen essential security tools, and dynamically rewrite commands if a download fails. If you are offline, it instantly falls back to a robust built-in configuration database. It turns a tedious afternoon of system troubleshooting into a flawless, hands-off setup.

🆔 @hackernewsgithubprojects

📦 dzhng/skills

Skills

Skills is the modular library that helps your AI agents build software autonomously instead of just writing lines of code. It changes how you work with AI by breaking massive development goals into small, independently verifiable slices, almost like clearing a fog of war. The project gives your agent structured procedures for everything from interviewing you to map out project unknowns, to performing visual screenshot reviews, and even rewriting its own development plans mid-run when things change. It turns AI assistants into systematic software factories that safely test and verify their own work until the goal is truly done.

🆔 @hackernewsgithubprojects

📦 meituan-longcat/sglang-fluentllm

Sglang-fluentllm

Sglang-fluentllm is the high-performance inference engine that finally stops hardware bottlenecks from slowing down your largest AI models. By combining model design directly with system engineering, this clever tool refactors how computers process text generation. It merges multiple decoding steps into a single, unified execution path on the graphics card, which dramatically cuts down on wasted processing overhead. This means your large language models can handle massive conversation histories and complex tasks without hitting a performance wall or lagging mid-sentence. If you want to run massive open-source models at maximum efficiency, this is the smart engine to deploy.

🆔 @hackernewsgithubprojects

📦 storybloq/storybloq

Storybloq

Keep your AI coding assistants from forgetting yesterday's work by turning your session history into active context. While most AI models start every session completely blank, this tool creates a dedicated folder in your repository to store tickets, issues, handovers, and lessons learned as simple files. It works as an MCP server and a CLI tool, allowing assistants like Claude Code to read your active roadmap, pick up where you left off, and even run autonomous workflows through planning and testing. It helps you build on top of past decisions instead of resetting your progress every single time you start coding.

🆔 @hackernewsgithubprojects

📦 scanopy/scanopy

Scanopy

Scanopy is the network documentation tool that automatically keeps your infrastructure diagrams up to date. Instead of spending hours manually sketching network setups in drawing apps only for them to go stale a week later, you just run a single background scanner. It automatically builds and schedules continuous updates for four distinct maps, showing you everything from physical switches and logical subnets to active workloads and application dependencies. It is perfect for anyone wanting a true, live picture of their home lab or company servers without installing software on every single device. Best of all, you can easily export the results to share with your team.

🆔 @hackernewsgithubprojects

📦 numman-ali/n-skills

n-skills

n-skills is the plugin marketplace that finally lets you write AI agent skills once and run them on any platform. While AI tools are evolving fast, they all use different formats, which means your custom prompts and workflows get locked into specific ecosystems. This repository solves that by offering a curated, cross-platform library of high-quality plugins using a single universal standard. You get pre-made skills for browser automation, multi-agent coordination, and repository maintenance that work natively with Claude Code, Copilot, Cursor, and Codex. It is the perfect setup to instantly give your local AI agents superpowers without rewriting code.

🆔 @hackernewsgithubprojects

📦 bytedance-seed/depth-anything-3

Depth Anything 3

You can now reconstruct incredibly detailed 3D scenes from a handful of random images without even knowing the camera angles. Depth anything 3 achieves this by treating the visual space as a simple field of light rays, eliminating the need for complex, heavy architectures. By using a single plain transformer, this model predicts highly consistent multi-view depth, estimates camera poses, and can even output high-fidelity 3D Gaussians for virtual flythroughs. It is incredibly useful for developers building spatial computing tools, robotic vision, or virtual reality projects. Check it out to easily bring flat images into the third dimension.

🆔 @hackernewsgithubprojects

📦 prat011/awesome-llm-skills

Awesome LLM Skills

Teach your favorite AI assistants how to handle specialized, repetitive tasks with customized workflows. The awesome-llm-skills repository is a curated collection of pre-made templates and guides that let you inject fresh capabilities directly into AI command-line tools and desktop apps. Instead of writing massive prompts every single time, you can equip your digital assistants with specific blueprints for organizing messy files, generating changelogs, or even analyzing meeting transcripts. This means your tools can automatically trigger the right workflow for the job, making your daily automation feel truly seamless. Grab a skill, drop it in your local folder, and watch your assistant get smarter.

🆔 @hackernewsgithubprojects

📦 shepherd-agents/shepherd

shepherd

Run your AI agents inside a reversible, Git-like playground where you can safely preview every file change before it ever touches your real directory. That is exactly what this clever library makes possible. Instead of letting an AI agent loose on your actual codebase, it runs the task inside a secure sandbox and saves the work as a reviewable proposal. You get a durable execution trace that lets you inspect, run, select, or discard the proposed changes with simple commands. It makes AI development incredibly safe and stress-free because you remain the ultimate gatekeeper of your code.

🆔 @hackernewsgithubprojects

📦 ekwek1/soprano-factory

Soprano Factory

You can now train a custom text-to-speech model that generates voice audio at up to two thousand times real-time speed on a standard graphics card. A clever new training toolkit called soprano-factory packages this process into a tiny six-hundred-line script. It lets you feed in your own voice recordings to teach a lightweight, eighty-million parameter model how to speak like you, a friend, or any character you want. The resulting voice is crystal clear and runs on a normal laptop using almost no memory. If you want to build super fast, custom voice models on your own hardware, this is the perfect place to start.

🆔 @hackernewsgithubprojects

📦 harrrshall/tinyrouter

TinyRouter

Tinyrouter is the tiny coordinator that finally makes multiple AI models work together as a single, smarter team. Instead of relying on one expensive LLM to do everything, this clever system uses a minuscule ten-thousand-parameter brain that looks at your question and decides which specialist model to call and what role it should play, whether that is a math genius, a factual writer, or a strict verifier. By training this tiny router through evolutionary trial-and-error rather than complex reinforcement learning, it consistently beats any single model on its own. It is the ultimate way to orchestrate open-source models on a budget.

🆔 @hackernewsgithubprojects

📦 handy-computer/transcribe.cpp

Transcribe.cpp

You can now run over sixty different speech-to-text models locally on your own hardware using a single lightweight library. This is transcribe.cpp, an open-source library built on the ggml runtime that lets you run transcription models on your CPU or GPU without heavy external dependencies. It supports sixteen major model families like Whisper, Canary, and Moonshine, offering both batch processing and real-time streaming. The project provides official bindings for Python, TypeScript, Rust, and Swift, making it incredibly easy to integrate local, high-performance transcription directly into almost any application. Check it out to build private, lightning-fast voice features today.

📰 https://news.ycombinator.com/item?id=48744571

🆔 @hackernewsgithubprojects

📦 hkuds/openphone

OpenPhone

Control your smartphone autonomously using a local AI model that runs entirely on your device. OpenPhone is an open-source, three-billion-parameter vision-language model designed specifically to interact with mobile apps without relying on expensive, slow, or privacy-invasive cloud APIs. Instead of wasting time and money calling a large model for every single screen tap, this system builds a visual map of your favorite apps and replays routine actions instantly as local macros. The smart model only steps in when you ask for something complex or completely new, giving you blazing fast, secure, and cost-free automation right in your pocket.

🆔 @hackernewsgithubprojects

📦 zack0x01/payment-bypass-bug-lab

payment-bypass-bug-lab

The payment-bypass-bug-lab is the interactive playground that teaches you security testing by letting you legally hack your way past digital paywalls. Designed for curious minds, this project runs a local web application containing real-world flaws often found in actual online stores. You get to play the role of a security researcher, learning how to manipulate network requests to drop a purchase price to zero, dig out hidden direct links to premium files, or change your user profile status to paid. It is a brilliant, hands-on way to understand web vulnerabilities safely on your own computer.

🆔 @hackernewsgithubprojects

📦 osmantic/ods

ods

Turn your personal computer into a fully private, self-hosted artificial intelligence powerhouse without spending a weekend wrestling with complex code or configuration files. This project automatically scans your machine, figures out exactly what graphics card you have, and instantly configures a complete local server stack with everything pre-wired and ready to roll. Instead of manually stitching together complicated tools, you get a clean chat screen, offline image generation, voice capabilities, and smart automated assistants talking to each other out of the box. It keeps your data completely offline and under your control. Run your own private virtual assistant directly on your home hardware today.

🆔 @hackernewsgithubprojects

📦 zhaozhaozhiyi/xiaochuangx

Xiaochuangx

Build and customize professional presentations, interactive video screenplays, and parametric three-dimensional designs entirely through specialized digital assistants. Xiaochuangx is an open-source workstation that connects diverse AI agents to specific creation workflows. Instead of relying on generic chat windows, it matches your tasks with dedicated, skill-based companions. You can orchestrate precise slide generation, script out video stages with voiceovers, or generate raw physical models using programmatic tools. It bridges high-level artificial intelligence with practical, production-ready outputs. It is a highly practical toolkit for any developer looking to build structured, agent-driven applications that go far beyond basic text chat.

🆔 @hackernewsgithubprojects

📦 moli13337/arcaea-6.14.11c

arcaea-6.14.11c

You can host your own fully functional private server for the rhythm game Arcaea, complete with every single song and character unlocked right out of the box. This clever toolkit lets you run a local Flask-based server that handles everything from instant registration to multiplayer lobbies. It even includes a custom patching utility for the game client that bypasses security checks and redirects traffic to your new server, all without needing to root your Android device. It is a fantastic way to experiment with multiplayer features, customize your gameplay experience, and explore your favorite tracks on your own terms.

🆔 @hackernewsgithubprojects

📦 zjunlp/skillx

SkillX

AI models usually have to relearn how to use their tools from scratch every single time, but SkillX changes that by automatically building a permanent, reusable skill library for agents based on their past mistakes and successes. Instead of saving messy, giant chat histories, this clever framework distills raw experience into a neat, three-tier library of planning, functional, and atomic skills. You can even take a skill library built by a giant model and plug it directly into a smaller, cheaper model to give it an instant ten-percent performance boost. It is like giving your code an automated playbook that actually gets smarter over time.

🆔 @hackernewsgithubprojects

📦 realchendahuang/sub-store-cloudflare

sub-store-cloudflare

You can now merge all your internet proxy subscriptions, filter out dead nodes, and generate custom routing rules without managing a single server. This clever tool runs entirely on Cloudflare Workers and a D1 database, meaning you get a lightning-fast web dashboard that costs absolutely nothing to host. You simply feed it your various subscription links or raw node text, apply built-in filters to rename or deduplicate nodes, and it outputs one clean, perfectly structured link tailored to your favorite client. It is incredibly easy to set up with a single-click deploy button, giving you complete control over your network routing directly from the cloud.

🆔 @hackernewsgithubprojects