📦 umputun/agterm

agterm

agterm is a native macOS terminal designed specifically to keep your screen organized when running multiple AI coding agents at once. Instead of losing track of background tasks in a sea of standard terminal tabs, this app groups your active shells into named workspaces so you can run several agent-driven sessions side by side. It embeds the high-performance Ghostty rendering engine for speed, but adds smart sidebar indicators that show whether an agent is active, blocked, or finished. With a built-in control API and a command-line tool, you can automate layouts, trigger overlays, and manage sessions entirely through scripts. It is the ultimate terminal setup for developers who want to...

🆔 @hackernewsgithubprojects

📦 majoorwaldi/comfyui-majoor-assetsmanager

ComfyUI Majoor Assets Manager

Managing thousands of AI generations just got incredibly simple because comfyui-majoor-assetsmanager lets you inspect the exact node workflow used to create any saved image without ever leaving your canvas. Acting as a media library built directly into ComfyUI, it lets you browse, rate, and tag your outputs in a fast virtual grid. Its standout feature is the Graph Map, a companion viewer that visually reconstructs the saved workflow inside your image and lets you copy or transfer parameters directly back to your workspace. It is a brilliant way to keep your generations organized and easily reproducible.

🆔 @hackernewsgithubprojects

📦 clickhouse/raytracer

Raytracer

Developers have built a fully functional 3D path tracer entirely out of ClickHouse SQL queries. There are no external programs or plugins here; a single database SELECT query calculates every single pixel, rendering glass-like chrome lettering floating over a procedurally generated landscape. It treats pixels as database rows, calculates complex 3D math on database tuples, and runs mirror-bounce loops using array functions to keep everything running in parallel. While other database engines struggle to even compile a scene like this, this clever hack whips through a gorgeous high-resolution image in under eighteen seconds. It is a brilliant, slightly chaotic reminder of just how powerful database engines can be when you...

📰 https://news.ycombinator.com/item?id=48747407

🆔 @hackernewsgithubprojects

📦 jay-sahnan/signal

Signal

Signal is the open-source sales assistant that finally lets you run smart web monitoring and email outreach on your own API keys. Instead of paying massive monthly fees for black-box software, this self-hosted workspace tracks company changes like new job openings or pricing shifts, collects contact info from around the web, and drafts personalized emails. It even uses browser automation to scrape websites that do not have public APIs. You get a clean chat interface powered by Claude to manage your list, and everything runs directly on your own database. It is the perfect way to build a custom pipeline while keeping full control of your data.

🆔 @hackernewsgithubprojects

📦 ohad6k/ditto

Ditto

Stop teaching your AI agents who you are every single time you start a new chat session. You already have months of honest, unfiltered coding history sitting in your local files, and this clever tool lets you mine those raw logs to generate a personalized agent profile. It strips out the noise and uses your own coding assistant to analyze your real habits, finding exactly what you reject, how you write, and what done actually means to you. You get a local markdown profile that hooks directly into your favorite developer tools, so your assistant instantly knows how you work. Try it out to see what surprising developer traits you...

🆔 @hackernewsgithubprojects

📦 sceneworks/sceneworks

SceneWorks

SceneWorks is the desktop-native AI art studio that finally runs heavy image and video generation locally on your GPU with absolutely zero Python or Docker required. Instead of wrestling with complex setups or paying subscription fees to cloud servers, you just run a single installer on your Mac or Windows machine. It uses native Rust engines to power everything from text-to-image creation to training your own custom character models right on your hardware. Your prompts, models, and creations stay entirely private. It is like having a fully loaded, professional AI workstation that just works, completely offline, straight out of the box.

🆔 @hackernewsgithubprojects

📦 narbehouse/benny-s-accessibility-hub-2.0

Benny's Accessibility Hub 2.0

This remarkable computer suite lets users navigate an entire digital world using only two head switches mapped to the spacebar and enter key. Designed by dedicated caregivers for a nonspeaking developer with quadriplegia and vision challenges, the project package includes eighteen customized games and a complete suite of communication tools. It features an incredibly clever real-time translation board that listens to surrounding conversation locally, then uses artificial intelligence to generate context-aware phrase suggestions and word completions to help the user participate instantly. This beautiful open-source resource is a masterclass in highly personalized, compassionate engineering that changes what is possible for assisted computing.

🆔 @hackernewsgithubprojects

📦 antigmalabs/ante-preview

Ante Preview

An open-source tool called ante-preview lets you run a fully self-contained coding agent directly inside your terminal with absolutely zero external dependencies. Unlike alternative tools that drag in massive runtimes and lock you into specific cloud models, this tool is packed into a single, fifteen-megabyte Rust binary that can run completely offline using local models. It includes its own embedded search and version control tools, utilizing up to seven times less memory than similar terminal agents. It is the perfect lightweight assistant for writing, editing, and running commands right from your command line.

🆔 @hackernewsgithubprojects

📦 openmoss/moss-transcribe-diarize

moss-transcribe-diarize

The open-source model moss-transcribe-diarize beats both Google and OpenAI in transcription and speaker-tracking accuracy on challenging multi-speaker benchmarks. Instead of the usual headache of gluing together separate transcription and speaker-labeling tools, this clever system does everything at once in a single, unified pass. It takes raw, messy audio from meetings, podcasts, or videos and outputs a clean transcript with exact timestamps and clear speaker tags already baked in. You can run it locally, serve it with high-speed inference engines, or use its built-in subtitle web app to burn captions straight to video. It is a brilliant, self-contained way to make sense of long-form conversations.

🆔 @hackernewsgithubprojects

📦 cloudrift-ai/emmy

Emmy PyTorch Compiler

You can compile PyTorch models directly into raw, optimized CUDA kernels using a custom compiler stack written in just five thousand lines of Python. An open-source tool called emmy lets you trace any PyTorch module, decompose it, and fuse the operations into highly efficient hardware-native instructions. Instead of dealing with massive, opaque compiler frameworks, you get to inspect your model across six distinct stages of intermediate representation all the way down to the final CUDA code. It makes optimization completely transparent, allowing you to easily benchmark your custom kernels, run experiments, and deploy tuned models to GPU servers.

🆔 @hackernewsgithubprojects

📦 jfrog/boost

Boost

Slash the token bill of your coding assistants by wrapping your terminal commands. This command-line utility intercept output from build, test, and package tools and condenses noisy terminal logs into ultra-compact, structured context. Instead of letting thousands of lines of install logs or repetitive build layers eat up your model's context window, it preserves only the critical details your agent needs to reason, like error messages, test failures, and timing statistics. This keeps your agents fast and accurate without wasting money. You can even run a report in your browser to see exactly how many tokens you saved.

🆔 @hackernewsgithubprojects

📦 harshaneel/humanize

Humanize

Write text that reads as genuinely human-authored by applying research-backed writing tweaks directly inside your favorite AI chat agent. This clever open-source repository contains humanize, a rule-based system prompt designed to strip away unmistakable AI writing patterns. By injecting natural sentence length variety, slashing predictable transition words, and matching your personal writing style from a quick sample, it helps your drafts sound authentic. It even includes a second forensic tool called ai-check to audit your work for hidden machine-generated signals. It is a brilliant, zero-dependency way to make your AI writing sound like an actual person wrote it.

📰 https://news.ycombinator.com/item?id=48820564

🆔 @hackernewsgithubprojects

📦 zymazza/mazzap

Mazzap

Mazzap is the 3D digital-twin engine that transforms open geospatial data into an interactive, self-contained virtual land model right in your browser. Unlike traditional mapping software, it runs completely locally with zero cloud dependencies, allowing you to click anywhere to read exact GPS coordinates, simulate active wildfires, and trace water flow paths across real terrain. It combines local astronomy, viewshed calculations, and vegetation mapping into a lightweight browser viewer. You can even query the land using natural language with a built-in assistant. It is a brilliant tool for visualizing how water, fire, and sunlight interact with the physical world.

📰 https://news.ycombinator.com/item?id=48806109

🆔 @hackernewsgithubprojects

📦 pglayers/pglayers

pglayers

The PostgreSQL distribution that packages extensions as ready-to-use Docker image layers, letting you mix and match features with zero compilation. Normally, official Postgres Docker containers ship entirely empty of extensions, forcing you to manually install dependencies or compile things like geospatial tools and vector search from source. This project publishes over fifty popular extensions as isolated, pre-built Docker layers. You simply stack them onto the official Postgres base image using a single copy line per extension in your Dockerfile. It completely eliminates file conflicts and manual setups. Grab the pre-configured full bundle or build your own custom database stack in seconds.

📰 https://news.ycombinator.com/item?id=48749752

🆔 @hackernewsgithubprojects

📦 servicenow/enterpriseops-gym

EnterpriseOps-Gym

EnterpriseOps-Gym is the interactive sandbox that finally tests how AI agents handle messy, multi-step office work instead of just answering trivia. While most benchmarks use simple text files, this project builds a containerized environment mimicking real corporate infrastructure across eight departments, from HR to customer service. It throws over a thousand expert-curated tasks at your agent, forcing it to navigate hundreds of tools and databases. Instead of just checking if the AI typed the right words, it runs verification queries to see if the actual environment state changed correctly. It is a brilliant reality check proving that autonomous office assistants still have a long way to go.

🆔 @hackernewsgithubprojects

📦 aerovato/magic-compact

Magic Compact

Magic Compact stops AI coding assistants from losing their minds by changing how they compress chat histories. Instead of flattening your entire programming session into a single generic paragraph that gives the AI amnesia, this tool condenses past assistant responses into local, high-fidelity summaries while leaving your original instructions and tools completely intact. Massive files and tool outputs are pruned to save tokens, but you can instantly pull them back on demand using a dedicated retrieval tool. It is a brilliant way to slash token costs and preserve the model's memory during long development sessions. Give it a try to keep your AI context clean and sharp.

🆔 @hackernewsgithubprojects

📦 egorshest/webgl-ascii-hero

webgl-ascii-hero

You can transform any standard 3D model into an interactive piece of retro terminal art directly inside a modern web browser. A project called webgl-ascii-hero is a boilerplate for Next.js that renders 3D files and instantly processes them into animated ASCII text using custom graphics shaders. Instead of just showing a flat image, this setup lets visitors drag to rotate the model and watch the character grid dynamically recalculate in real time. It even layers on retro CRT scanlines and glow effects that react to the cursor. It is a fantastic starting point for building a highly memorable website landing page.

🆔 @hackernewsgithubprojects

📦 cyl19970726/poly-sdk

Poly-SDK

This single TypeScript SDK lets developers interact with every layer of Polymarket, from placing advanced limit orders to orchestrating automated arbitrage strategies. Instead of juggling fragmented official APIs and smart contracts, poly-sdk wraps trading services, on-chain contract actions, and live WebSocket price feeds into a unified toolkit. It even simplifies the mathematical mirror properties of prediction market orderbooks to prevent double-counting. For developers building trading bots or copy-trading platforms, this tool manages rate limits, caches active data, and handles complex split and merge operations under the hood, making it a reliable foundation for building custom trading tools.

🆔 @hackernewsgithubprojects

📦 deepfoldprotein/patchr

patchr

Most experimental molecular structures in the Protein Data Bank are missing critical parts like flexible loops or unresolved sidechains. Patchr fixes this by using diffusion-based AI to perfectly fill in the blanks while keeping your original, hard-won coordinates exactly as they are. It works across proteins, DNA, RNA, and complex multi-chain structures, boasting a ninety-nine percent chain connectivity success rate. Even better, you can go straight from fixing your molecular structure to running molecular dynamics simulations in Gromacs or Amber. It is like content-aware fill, but for the fundamental building blocks of life.

📰 https://news.ycombinator.com/item?id=48835428

🆔 @hackernewsgithubprojects

📦 chrishayduk/nanofold-competition

nanofold-competition

AI models usually get smarter by throwing mountains of data at them, but biology does not work that way because high-quality protein data is incredibly scarce. The nanofold-competition repository turns this bottleneck into a brilliant slowrun tournament where developers compete to build the most data-efficient protein folding models. Everyone gets the exact same budget of ten thousand protein structures and is challenged to see who can learn complex physical geometry fastest. By restricting training sizes and evaluating how quickly your model learns, this project forces you to design smarter biological priors instead of just renting more GPUs. It is a fantastic playground for anyone wanting to test their machine learning...

🆔 @hackernewsgithubprojects