📦 mathews-tom/archex

Archex

Stop burning your AI agent's context window on endless backtracking. archex lets you gather, rank, and bundle the exact code, type definitions, and structural context your agent needs before it even starts reasoning. Running entirely locally with zero hosted inference or API keys, it analyzes your repository and returns a token-budgeted context bundle alongside an explanatory receipt that proves what was included or skipped. By handling the heavy lifting of dependency mapping and code retrieval up front, it saves precious tokens and ensures your AI has everything it needs to act. Simply run it through your command line or plug it directly into Claude Code as an MCP server for...

🆔 @hackernewsgithubprojects

📦 professorpalmer/puppetmaster

Puppetmaster AI

Puppetmaster turns the AI agents you already use into a coordinated swarm of background workers that cost up to ninety-eight percent less to run. Instead of wasting expensive tokens on long chat histories, this tool runs independent worker processes in the background and writes their discoveries directly into local SQLite databases. It automatically routes every task to the cheapest model that can handle it and lets you do follow-up reads instantly for zero tokens. It is like having a smart project manager that organizes messy, multi-file engineering tasks while keeping your API spend locked down. You should give it a try.

📰 https://news.ycombinator.com/item?id=48338669

🆔 @hackernewsgithubprojects

📦 huggingface/pi-llama

pi-llama

Run and manage your local AI models right inside your terminal assistant by connecting your coding agent directly to a running server. The pi-llama repository bridges the gap between the Pi coding agent and llama.cpp. Instead of manually configuring API endpoints, this extension automatically discovers which models are running on your machine, dynamically detects their context windows, and registers them instantly. It even shows you real-time progress bars as your computer loads model weights into memory. Grab this extension to turn your local machine into a private, offline development powerhouse.

🆔 @hackernewsgithubprojects

📦 elara-labs/code-context-engine

Code Context Engine

Feeding an entire codebase into an AI assistant is a fantastic way to burn through your budget, but code-context-engine stops the bleeding by cutting AI input token costs by up to ninety-four percent. Instead of forcing your developer tools to re-read giant files every single session, this clever local tool parses your code into smart semantic chunks and runs a hybrid search right on your machine. It hooks into editors like Cursor and Claude Code, allowing your AI assistant to search for specific code snippets rather than swallowing entire files. It even tracks your real-time dollar savings on a local dashboard.

📰 https://news.ycombinator.com/item?id=48803896

🆔 @hackernewsgithubprojects

📦 funador/claude-code-merge-queue

Claude Code Merge Queue

Your laptop doesn't have to melt just because four parallel Claude Code agents are trying to run heavy builds and push their code at the exact same time. The open-source tool claude-code-merge-queue is a local, zero-cost merge queue that acts like traffic control for your AI coding sessions. Instead of letting concurrent agents trigger flaky database tests or race each other’s git pushes, this tool serializes builds and lands changes one at a time. It runs entirely on your own machine using smart, crash-safe locks, saving you from expensive cloud-runner bills. You get clean history and zero-cost safety without any coordination headaches.

🆔 @hackernewsgithubprojects

📦 pozzettiandrea/comfyui-unirig

comfyui-unirig

Comfyui-unirig is the ComfyUI extension that lets you automatically generate functional skeletal rigs for 3D character meshes directly in your node editor. Instead of spending hours manually placing joints and painting weight maps, this tool uses advanced computer vision models to analyze your 3D models and instantly build an animatable skeleton. It bundles everything you need, including a built-in instance of Blender, so you can easily change poses, skin your models, and export the finished animations. It makes the notoriously difficult process of 3D character rigging accessible to anyone building creative pipelines.

🆔 @hackernewsgithubprojects

📦 tranvuongquocdat/sidescreen

sidescreen

You can now turn any spare Android tablet into a fully functional second monitor for your Mac, completely bypassing Apple's iPad-only restrictions. An open-source project called sidescreen makes this happen using either a USB-C cable or wireless connection. It is not just mirroring your desktop; it creates a true virtual display with full touch support and sharp Retina scaling. By utilizing hardware-accelerated video streaming, it keeps lag under sixteen milliseconds so dragging windows and tapping buttons feels incredibly responsive. It is the perfect way to give an old tablet a second life as a highly portable productivity companion.

🆔 @hackernewsgithubprojects

📦 aiming-lab/simplemem

Simplemem

Simplemem is the unified memory stack that finally gives AI agents a highly efficient, self-evolving long-term memory across text, images, audio, and video. Most memory systems either overwhelm models with massive chat histories or burn through tokens with constant, slow reasoning loops. Instead, this project uses a clever three-stage pipeline to compress interactions into compact, lossy-free facts right when they happen. Even better, it features an autonomous self-evolution loop that constantly diagnoses its own retrieval mistakes and adjusts its search settings over time. It is a brilliant way to make AI assistants remember past context perfectly while slashing token costs.

🆔 @hackernewsgithubprojects

📦 nikhilkain/vyxel-apps

Vyxel Apps

Install and update your favorite open-source Android apps directly from their GitHub releases. This clever platform bypasses traditional app stores by turning GitHub into a completely decentralized, ad-free marketplace. It automatically detects your device's architecture to fetch the correct installation file, and even monitors the background to notify you when new updates are available. You get built-in safety tools like a trust score based on repository activity, and a comparison mode to inspect different apps side by side. It is the perfect way to safely explore community-driven mobile software without any tracking. Give it a spin to customize your mobile experience today.

🆔 @hackernewsgithubprojects

📦 shadcn/improve

Improve

Improve is the codebase advisor that acts like a senior architect, mapping your repository to write flawless implementation specs for cheaper AI models to execute. Instead of burning expensive tokens on basic coding tasks, it analyzes your code, identifies security flaws or performance bottlenecks, and generates self-contained markdown plans. These specs are so detailed, complete with testing boundaries and strict stop conditions, that any lightweight model can run them in an isolated workspace without losing context. It is the perfect way to let your smartest AI do the heavy thinking while leaving the tedious execution to cheap, fast assistants.

🆔 @hackernewsgithubprojects

📦 michalparkola/tapestry-skills

Tapestry Skills

tapestry-skills is the productivity toolkit that finally turns passive learning into immediate action for your AI agent. Instead of just reading articles or watching videos, you just type one command with a link, and your AI automatically strips away the clutter, grabs the core transcript or text, and formats a concrete action plan. It solves the trap of endless consumption by mapping out five progressive milestones you can actually ship. Whether you are stuck on a vague task or drowning in open tabs, it forces you to focus on building rather than planning. Give it a spin and start shipping.

🆔 @hackernewsgithubprojects

📦 heyitsnoah/claudesidian

Claudesidian

Turn your Obsidian vault into an AI-powered thinking partner by letting Claude Code work directly with your markdown notes. Claudesidian organizes your entire second brain using the popular PARA method, setting up dedicated spaces for your active projects, resources, and archives. Instead of just generating drafts, this setup lets you interact with a smart local assistant that searches your vault, makes clever connections, and asks deep questions to flesh out your ideas. It even ships with pre-configured skills like daily reviews and research assistants. It is the ultimate local setup to finally make your personal notes work for you.

🆔 @hackernewsgithubprojects

📦 iisu-network/iisu

iisu Android Emulation Launcher

Your Android gaming handheld is about to get a serious visual upgrade. A clever project called iisu completely replaces your standard, boring mobile home screen with a gorgeous, visuals-first console interface built specifically for gaming. Instead of squinting at tiny app icons, you get a clean, console-style dashboard to display and launch your entire retro library. It even hooks directly into RetroAchievements, letting you track your trophies and view box art right from the game selection menu. If you want your handheld to actually feel like a dedicated gaming console rather than a phone with buttons, this is the launcher to grab.

🆔 @hackernewsgithubprojects

📦 xalgord/xalgorix

xalgorix

This modular repository defines structured, machine-readable security skills designed to coordinate autonomous agents across specialized assessment tasks. By breaking down complex activities like container escape testing and cryptographic audits into standardized instruction templates, the project allows autonomous agents to dynamically coordinate and execute complex workflows without manual programming. It solves the challenge of scaling security automation by creating a common language that links high-level agent directives to concrete execution blueprints. Security teams can use this framework to build highly customized, self-orchestrating scanning loops that continuously test modern application stacks from end to end.

📰 https://news.ycombinator.com/item?id=48805464

🆔 @hackernewsgithubprojects

📦 christopherkarani/swarm

Swarm

Swarm is the multi-agent framework that finally makes building AI workflows on Apple platforms completely crash-proof. Instead of dealing with clunky Python setups, this pure Swift powerhouse lets you build complex, multi-step pipelines that compile into a safe directed graph. The best part is its crash-resumable execution, meaning if your app crashes mid-workflow, you can instantly spin it back up and resume exactly from your last step. You get type-safe tools, local or cloud models, and parallel execution built natively into Swift. It is the perfect tool for building robust, intelligent workflows that just work.

📰 https://news.ycombinator.com/item?id=48805437

🆔 @hackernewsgithubprojects

📦 huggingface/tau

Tau

Tau is a minimalist terminal coding agent that doubles as a masterclass on how coding-agent systems are actually built. It lets you write natural commands to edit files, run bash scripts, and troubleshoot error messages right from your command line. The coolest part is that it avoids the giant, messy codebases of typical AI tools by splitting itself into clean, independent layers. The central brain stays completely separate from the visual user interface, communicating entirely through a steady stream of simple events. It is a brilliant, readable project for any developer who wants to understand how agent loops really function under the hood.

📰 https://news.ycombinator.com/item?id=48805749

🆔 @hackernewsgithubprojects

📦 tutti-os/tutti

Tutti

The collaborative operating system that actually lets your AI agents work together without you playing middleman. We all love using powerful coding assistants, but the moment you need one agent to write an API and another to build the frontend, you end up copy-pasting code, files, and context back and forth like a glorified messenger. Tutti solves this by giving your agents a real-time shared workspace where they share the exact same files, active tasks, and context history. Your design agents and coding agents can finally interact, see each other's edits, and hand off work natively. Check out Tutti to make your agents sync up.

🆔 @hackernewsgithubprojects

📦 stevibe/benchlocal

BenchLocal

BenchLocal is the local-first desktop app that finally lets you test and compare AI models side-by-side on real, practical tasks. Instead of relying on abstract academic scores, it runs installable benchmark packages directly on your machine to evaluate how different models handle actual programming, math, and logic problems. You can plug in local or remote models, customize the settings, and watch them compete. It even features a built-in agent control surface, allowing external AI tools to run and inspect tests automatically while the desktop interface stays live. It is the perfect playground for finding the exact right model for your specific workflow.

📰 https://news.ycombinator.com/item?id=48804450

🆔 @hackernewsgithubprojects

📦 insta360-research-team/unisharp

unisharp

unisharp is the open-source tool that lets you turn a single flat photo into a fully explorable 3D scene, no matter what kind of camera captured it. Traditionally, creating 3D views from one image required standard, straight-on shots. This project changes that by handling everything from ultra-wide fisheye lenses to full panoramas. It instantly predicts the 3D structure of the space using virtual tiny points called Gaussians, letting you virtually fly around inside your static image. Whether you are working with action camera footage or indoor room scans, you get sharp, realistic new perspectives from a single click.

🆔 @hackernewsgithubprojects

📦 weirdmachine64/ghidragpt

GhidraGPT

GhidraGPT is the Ghidra plugin that finally brings the intelligence of modern language models directly into your reverse engineering workflow. If you have ever stared at a wall of messy, decompiled assembly code trying to figure out what it actually does, this tool is a lifesaver. It lets you right-click any confusing function to instantly explain the logic, detect security vulnerabilities, and even automatically rename variables and update types to make the code look like a human wrote it. It is like having an expert developer sitting next to you, translating cryptic binaries into clear, readable explanations in real time.

🆔 @hackernewsgithubprojects