📦 devkitshq/notifkit

Notifkit

You can now handle emails, SMS, push notifications, and webhooks with a single typed API call that is completely self-hosted inside your own stack. This open source infrastructure is called notifkit, and it acts as a central brain for your product notifications. Instead of manually writing complex code for retries, timezone-aware quiet hours, user opt-outs, and channel fallbacks, you let this engine run the show. It sits directly on top of your PostgreSQL and Redis databases to orchestrate everything behind the scenes. Best of all, it even includes an AI-agent-compatible server, meaning your development assistants can actually send updates or diagnose delivery failures on their own.

🆔 @hackernewsgithubprojects

📦 pixel-agents-hq/pixel-agents

Pixel Agents

Turn those boring command line AI agents running in your terminal into animated pixel art characters working in a miniature virtual office. This project monitors your active AI sessions and translates their real-time operations into visual actions. You will watch your digital assistants walk over to their desks, sit down, type when they are editing files, read when they are searching, and pop up speech bubbles when they are waiting for your permission. You can even design the office layout with custom floors, walls, and furniture. It is the perfect way to make orchestrating a team of digital workers actually feel like a game.

📰 https://news.ycombinator.com/item?id=49470113

🆔 @hackernewsgithubprojects

📦 sv-grid/sv-grid

sv-grid

Build lightning-fast, interactive data tables in Svelte 5 with zero lag, even when scrolling through a million rows of data. Instead of wrapping an old JavaScript library in a bulky adapter, sv-grid is written from scratch specifically for the latest Svelte runes. This gives you a tiny, highly efficient engine that handles smooth row and column virtualization, spreadsheet-style cell editing, and complex row grouping right out of the box. It even includes a dedicated helper server to let artificial intelligence assistants write and refactor your table code flawlessly. It is the ultimate tool for bringing high-performance data management to modern web applications.

📰 https://news.ycombinator.com/item?id=49471036

🆔 @hackernewsgithubprojects

📦 experientiallabs/experiential

Experiential: The Gateway for AI Agents

Imagine a world where your AI agents don’t just guess which model to use, but actually learn from your real work to pick the perfect one every single time. That is exactly what Experiential does, acting as a smart gateway that sits between your code and the best AI brains available. It takes your actual usage history, studies what worked best for speed and quality, and automatically tunes its routing to save you money without sacrificing performance. This project is fascinating because it turns your daily interactions into a custom optimization engine that gets smarter the more you use it.

📰 https://news.ycombinator.com/item?id=49471407

🆔 @hackernewsgithubprojects

📦 cheat2001/angkorgit

AngKorGit: The 12 MB Git Client

AngKorGit is a Git client that fits in just twelve megabytes, yet handles massive codebases with the same speed as much larger tools. Most desktop apps for version control weigh over a gigabyte, often bogging down your machine with unnecessary bloat. This open-source project uses a lightweight engine to deliver a fast, beautiful interface without the heavy price tag. It brings daily Git tasks like viewing diffs and resolving conflicts into a simple, visual workspace that feels like a native app. You can browse commit graphs, manage branches, and even let AI review your code before you commit, all while staying in complete control.

🆔 @hackernewsgithubprojects

📦 pollen-robotics/microduck

Microduck: The Tiny Robot That Walks with AI

Microduck is the tiny biped duck robot that actually walks, stands up, and even quacks thanks to real reinforcement learning. This small, lightweight machine runs a sophisticated AI brain on a standard computer chip, driving fifteen servos to move naturally. The coolest part is its resilience: if you knock it over, it uses its sensors and learned policies to get back up on its own. It can even pick up objects with its beak and switch to a rolling mode if you attach wheels. The software is built in Rust for stability, featuring a safe update system that ensures the robot never gets bricked during an upgrade.

🆔 @hackernewsgithubprojects

📦 kelviq/tare

Tare: The Usage Detective for Claude Code

Tare acts as a digital detective for your Claude Code usage, solving the mystery of why your quotas drain so fast by reading the session logs already sitting on your machine. The tool performs a deep audit of your local activity, pinpointing exactly which files, tools, or background automations are silently consuming your tokens. It reveals the true cost of context, showing you how much is wasted when Claude re-sends old information instead of just the new input. Because everything runs locally, your private prompts and code never leave your computer, making it a safe way to diagnose limit hits.

📰 https://news.ycombinator.com/item?id=49467551

🆔 @hackernewsgithubprojects

📦 texel-org/windfoil

Windfoil: The AI-Born Rendering Trick

A single AI session produced Windfoil, a new algorithm that draws crisp 2D shapes with perfect anti-aliasing. It runs on your graphics card to calculate the exact amount of ink covering each pixel. Traditional methods often guess at edges, causing blurry or jagged lines on complex drawings. This new approach uses a winding integral to handle overlapping strokes and curves without extra cleanup steps. It solves a long-standing problem where thin lines or overlapping shapes would look messy or require heavy computer preprocessing. By computing coverage directly, it offers higher quality for things like generative art and detailed typography.

📰 https://news.ycombinator.com/item?id=49473043

🆔 @hackernewsgithubprojects

📦 miaai-lab/glm-5.3-flash-nvfp4-dual-dgx-spark

Run a Massive AI Model on Two Small Chips

Spin up a massive, multimodal AI model on just two small computer chips. This project gets a huge language model running on a pair of compact devices by splitting the workload across them using a smart networking setup. The biggest surprise is that it handles images and video while staying fast enough to be useful, proving you do not need a massive server rack to run advanced AI. It handles the complex wiring, memory management, and software setup automatically, so you can focus on using the tool. This is a clever way to build a powerful local AI helper at home without spending a fortune on hardware.

🆔 @hackernewsgithubprojects

📦 1038lab/comfyui-flashvsr

Real-time Video Upscaling in ComfyUI

ComfyUI-FlashVSR is the custom node that brings real-time video super-resolution directly into your ComfyUI workflow. It solves the problem of blurry, low-resolution video by using a diffusion model to upscale footage to 2x or 4x resolution without losing quality. The standout feature is its speed; it processes frames fast enough for streaming applications, thanks to optimized attention mechanisms and flexible model versions that fit different GPU memory limits. You can easily toggle between high-quality and fast-processing modes, and it even handles audio passthrough so your video stays in sync.

🆔 @hackernewsgithubprojects

📦 paoloanzn/pi-black

Pi Black: Use Your Claude Subscription

Pi Black lets you connect a third-party coding agent called Pi directly to your existing Claude Max or Pro subscription, completely bypassing the need for separate API keys. The project works by intercepting network requests and disguising them to look exactly like the official Claude Code application, ensuring the billing systems treat your new tool as a standard client. It handles the complex technical formatting required to pass authentication checks, including specific header calculations and identity verification. This is a clever workaround for developers who want to use their current flat-rate subscription across multiple different tools without paying extra for individual API usage.

📰 https://news.ycombinator.com/item?id=49473333

🆔 @hackernewsgithubprojects

📦 mirumo0u0/comfyui-cosmos-reference

Cosmos Gets Image Memory

The Cosmos model finally learned to look at your pictures. This new tool lets you feed a reference image directly into the latent space, essentially gluing it to your prompt so the AI can’t ignore it. It’s a brute force move that trades speed for raw visual fidelity, making sure every detail of your source material survives the generation process. While it runs a bit slower, it captures the essence of your input like a pro photographer would. If you need your AI images to actually match the source material, this is your cheat code for consistency.

🆔 @hackernewsgithubprojects

📦 tellahq/opensession

The AI That Lives on Your Computer

Open Session lets you run powerful AI coding agents directly on your own computer, giving you full control over your code. Unlike cloud tools that lock your work in the dark, this self-hosted server connects your Slack, Linear, and GitHub directly to an AI that actually writes and tests code in real git worktrees on your machine. It supports multiple AI models and lets you customize everything from the agent's persona to your specific repositories without forking the entire project. You get a secure, private environment where your data never leaves your infrastructure, and you can even use it from your phone via a simple web app.

📰 https://news.ycombinator.com/item?id=49473549

🆔 @hackernewsgithubprojects

📦 sapientinc/praxist

Praxist: The Autonomous Research Engine

Praxist is an autonomous system that runs a full scientific research loop without human intervention. It takes a project that already works and has a measurable goal, then coordinates parallel AI agents to explore different solutions. These agents test ideas, gather evidence, and use that data to guide the next round of experiments. This turns a static codebase into an active research process that can discover improvements you might not find manually. The system ensures every result is backed by verifiable evidence, making the entire process transparent and auditable. It is a powerful tool for developers who want their computers to do the heavy lifting of experimentation.

📰 https://news.ycombinator.com/item?id=49473502

🆔 @hackernewsgithubprojects

📦 db-aeon/joshu-oss

Joshu: Your AI Executive Assistant Workspace

Joshu builds a shared digital workspace where you and an AI agent operate the same software together, rather than the AI just typing on a screen. You run a private, self-hosted desktop on your own server that includes tools for email, a whiteboard, and a sandboxed browser. The agent can open files, search your notes by meaning, and handle tasks while you stay in the loop for sensitive actions. It’s a powerful way to create a persistent digital twin that actually works for you, not just against you.

🆔 @hackernewsgithubprojects

📦 naw103/foremerge

Foremerge: Catching AI Coding Agent Conflicts Before They Happen

Foremerge lets you catch intent conflicts before they turn into code disasters. Imagine two AI agents working on the same project in separate copies of your code. Git only sees text, so if one agent replaces a payment function and the other adds features to that same function, Git sees no overlap and merges them blindly. You end up with broken code that looks perfectly fine on the surface. Foremerge fixes this by having agents announce their plans first. They write down what they are about to change on a shared digital whiteboard stored inside your Git folder.

🆔 @hackernewsgithubprojects

📦 gabberflast/academic-pptx-skill

Make Claude Build Serious Academic Slides

Generate professional academic slides that actually argue a point, not just display data. This tool stops AI from creating flashy, empty decks and forces it to follow strict scientific standards instead. Every slide gets a clear title that states the main finding. The presentation flows like a logical story, with one chart per slide and proper citations. It removes unnecessary decorations so the science stands out. This is perfect for conference talks, thesis defenses, or grant proposals where you need to convince a skeptical audience with solid evidence, not just pretty pictures. Say goodbye to generic AI slides and get a deck that tells the real story.

🆔 @hackernewsgithubprojects

📦 tonyd2wild/glm-5.3-flash-nvfp4-2x-dgx-spark

GLM 5.3 Flash on DGX Spark

Run a massive, 320 billion parameter AI model on just two small desktop computers by fixing seven critical software bugs that had previously blocked everyone else. This repository provides the first known working setup for the GLM 5.3 Flash model on NVIDIA DGX Spark hardware, allowing it to process extremely long documents and generate text at high speeds. The creator solved deep technical issues in the underlying software stack to make this fast, energy-efficient hardware actually usable for such a large model. By sharing the exact fixes, the build files, and the performance tests, this project saves other developers weeks of trial and error.

🆔 @hackernewsgithubprojects

📦 tonyd2wild/glm-5.3-flash-nvfp4-dflash2-2x-dgx-spark

GLM-5.3 Flash on Spark: The First Working Setup

The first working deployment of the massive GLM-5.3 Flash model on two NVIDIA DGX Spark machines is finally here. This repository is not just code; it is a complete recipe for getting this thirty-two-billion-parameter model running on hardware that was previously impossible for it. The creator fixed seven critical bugs in the software stack, patching the engine to handle the unique memory layout of the new chips. The result is a stable server that can handle over two hundred thousand tokens of context, proving that even the most complex AI models can run on this compact, efficient hardware.

🆔 @hackernewsgithubprojects

📦 minnesotanlp/meta-n

Meta N: The AI That Codes Its Own Upgrades

Meta N is the research framework that makes AI agents upgrade their own code. Most systems just tweak final answers, but this project digs deeper. It uses a universal engine to read execution logs and write new helper functions directly into the agent's stack. Think of it as an AI that looks at its own mistakes and patches its own brain. This is not just theory; it is a working prototype that tests itself across nine major benchmarks, from legal reasoning to terminal commands. The result is a stack of self-improving layers that get better with every run. The takeaway?

📰 https://news.ycombinator.com/item?id=49458576

🆔 @hackernewsgithubprojects