📦 th1nhhdk/local_ai_ocr

Local AI OCR: Your Offline Text Scanner

Scan documents and images directly on your computer without uploading a single byte to the cloud. This project, Local AI OCR, lets you turn pictures and PDFs into editable text using a smart AI model that runs entirely on your own machine. It is perfect for privacy-conscious users who want fast results without trusting third-party servers with their sensitive papers. You simply drop your files in, and the tool handles the heavy lifting right there on your hard drive. It is a simple, portable way to get powerful text recognition without any internet connection required after setup. Just grab the software and start reading those scanned papers instantly.

🆔 @hackernewsgithubprojects

📦 financeflash/unvibecode

Unvibecode

You can now automatically map any complex, unfamiliar codebase into interactive business workflows and visual dependency graphs. A command line tool called unvibecode scans your repository locally, traces how your files and functions connect, and reconstructs how the software actually executes business operations. Instead of manually digging through hundreds of files, it builds an interactive visual map that highlights how data flows from entry points to real business outcomes, while identifying critical logic risks along the way. It also generates prepackaged, highly connected code chunks that you can feed directly to large language models for smarter context.

🆔 @hackernewsgithubprojects

📦 eugr/llama-benchy

Benchmark AI Models with llama-benchy

The most honest way to test an AI model isn't to see how smart it sounds, but how fast it actually thinks across different conversation lengths, and that is exactly what llama-benchy does. This clever Python tool bypasses the limitations of proprietary benchmarking suites by testing any OpenAI-compatible API endpoint with surgical precision. While most tools just measure raw speed, llama-benchy stress tests the model at varying context depths to reveal how performance degrades as conversations grow longer. It even isolates the impact of server-side caching by running two distinct steps to show you exactly how much faster the engine becomes when it recognizes previous text.

🆔 @hackernewsgithubprojects

📦 nikolay-tyulkin/watti

Watti: The Lamp That Learns to Move

Watti is a desk lamp that can move its own head to follow you around. It uses five motors and a depth camera to track your hands and light up only the part of the desk where you are working. You build scenes in a browser editor that sends full animations to a Raspberry Pi, which plays them smoothly without needing a constant internet connection. The lamp also has forty-five color LEDs and a camera for scanning your space. It turns a simple light into a small desktop assistant that reacts to what you do. You can check the roadmap to see what comes next.

🆔 @hackernewsgithubprojects

📦 bybit-exchange/kaas

KaaS — The Wiki That Writes Itself

KaaS is the self-hosted wiki compiler that turns messy notes into a structured, queryable library without relying on fuzzy vector search. Most knowledge tools just chunk your text into black-box embeddings, but this project actually reads and rewrites your documents into clean Markdown articles, creating a real tree of organized information you can browse. That means when you ask a question, the system picks the full articles it needs rather than guessing from fragments, and every answer cites the exact page it came from so you can verify it.

📰 https://news.ycombinator.com/item?id=49099857

🆔 @hackernewsgithubprojects

📦 salathleizhang/deepseek-harness-desktop

DeepSeek Harness Desktop

DeepSeek Harness Desktop lets you build and run custom AI agents with a clean interface, combining a chat-like workspace with a terminal for real-time control. The single most interesting part is its modular plugin system: you can write tiny, focused scripts called skills that teach the AI exactly how to use tools or edit files, turning a generic model into a specialized assistant without coding a whole app. It’s like giving your AI a custom toolkit where you decide which tools it gets and when. This setup is super handy for developers who want precise control over AI tasks without wading through complex setup procedures.

🆔 @hackernewsgithubprojects

📦 bikeshaving/termdom

Build Terminal Apps with HTML and CSS

TermDom is a JavaScript library that lets you build terminal apps using HTML, CSS, and the standard DOM. Instead of wrestling with raw ANSI codes, you write normal web code like flexbox layouts and style sheets, and the library handles the heavy lifting. It takes your HTML, calculates the layout in terminal cells, and paints it to the screen using ANSI escape sequences. It even listens for keyboard and mouse input, turning them into web events you can handle with standard JavaScript.

📰 https://news.ycombinator.com/item?id=49261987

🆔 @hackernewsgithubprojects

📦 rpatrik96/hallmark

Hallmark: The Citation Checker

Hallmark is the citation checker that finally helps you spot fake references in machine learning papers. After a recent scandal exposed hundreds of invented citations slipping through peer review, this project offers a standardized way to test if tools can actually distinguish real from fake. It contains over two thousand annotated examples sorted by how tricky they are to detect. You can run your own detection methods against it or compare them against top AI models and database tools to see what really works. This gives researchers a clear, fair yardstick to measure accuracy instead of just guessing. It is the perfect reference for anyone tired of trusting citations blindly.

🆔 @hackernewsgithubprojects

📦 openlabs-so/openanalytics

OpenAnalytics: Privacy-First Web Analytics

OpenAnalytics gives you the rare ability to track revenue from your Stripe account alongside every page view, all without using cookies or storing IP addresses. The system protects privacy by turning visitor identities into daily rotating hashes that expire every night, so you never build long-term profiles. You can watch exactly who is online right now with city-level locations resolved locally on your own server, ensuring no data ever leaves your hardware. The tracker script is kept tiny to avoid slowing down websites, and the whole stack is designed for easy self-hosting.

📰 https://news.ycombinator.com/item?id=49302597

🆔 @hackernewsgithubprojects

📦 snowteam2023/cognivia

Cognivia AI Therapy

Cognivia lets you talk with an AI that actually understands cognitive behavioral therapy. It listens to your worries, spots your negative thought patterns, and gives you rational responses to help you feel better. Think of it as a supportive chatbot trained by real therapists to guide you through tough feelings instead of just giving generic advice. It is a genuine tool for mental health support that helps you reframe your thoughts with care. Go check it out and see if it helps.

🆔 @hackernewsgithubprojects

📦 hrtan/fastmix

FastMix: Auto-Tune Data for LLMs

FastMix lets you automatically find the perfect data mix for training large language models without wasting weeks on trial-and-error. Instead of manually guessing which sources matter most, this tool trains a small helper model that watches how each data type affects performance. It then adjusts the proportions on the fly, boosting useful content and dialing back noise in real time. You get two clear paths: one that optimizes for general validation accuracy and another that fine-tunes for specific tasks like math or science. The code uses efficient kernels to keep training fast, and you can track progress through standard logs.

🆔 @hackernewsgithubprojects

📦 xufeiqiong/gama-bench

gama-bench

Large language models judge the exact same bad behavior differently depending entirely on whether a man or a woman did it. A new benchmark called gama-bench tests this by feeding top artificial intelligence models over a thousand mirrored conflict scenarios, changing only the gender of the person at fault. The results are fascinating. When a male character steps out of line, the models tend to write harsher, more punitive, and blaming responses. But when a female character does the exact same thing, the models suddenly shift to a soft, therapeutic, and highly empathetic tone. It is a brilliant way to expose hidden double standards in AI, showing us that our...

🆔 @hackernewsgithubprojects

📦 am-will/gooey-pi

GooeyPi: One Desktop for All Your Coding Agents

GooeyPi is the desktop workspace that lets you run Pi, OMP, and Prime Agent in the same window without switching apps. It solves the headache of juggling different coding tools by giving each agent its own familiar interface while keeping everything in one place. You can switch between workspaces using a simple top-left button, and each agent keeps its own sessions and models safely separate. This means you can work on multiple projects or test different AI models simultaneously without ever closing a window. It is perfect if you want the power of specialized agents but hate the clutter of dozens of open applications.

🆔 @hackernewsgithubprojects

📦 arcademakersources/arcademaker

ArcadeMaker 2D Game Engine

ArcadeMaker is the 2D game engine that actually lets you build cross-platform games using your own custom programming language. Inspired by the classic GameMaker workflow, it bundles a complete visual workspace, a sprite designer, and a custom scripting language called Exp into one lightweight tool. Instead of wrestling with complex setups, you can design rooms, paint sprites, and write your game logic inside a single program. Since it uses MonoGame under the hood, you can compile your creations for desktop, mobile, and even consoles. Grab your coffee and see how fun building games from scratch can be.

📰 https://news.ycombinator.com/item?id=49258085

🆔 @hackernewsgithubprojects

📦 trae1oung/swe-touch

SWE-Touch: Testing Code Agents with Human Intervention

SWE-Touch lets you evaluate how well coding assistants handle real-world changes by letting humans modify code during tests. It provides a benchmark where researchers can see how agents adapt when users actually touch and alter the codebase, rather than working in isolation. This approach reveals whether AI tools can truly collaborate with developers by adjusting to new requirements and fixes on the fly. It solves the problem of static testing that ignores the messy reality of human collaboration. You get to watch agents demonstrate resilience and flexibility as they react to live edits.

🆔 @hackernewsgithubprojects

📦 pkucs-ltf/refcaptioner

RefCaptioner: Grounded Video Descriptions

RefCaptioner is the open-source model that turns video footage into precise, image-anchored stories. Instead of just describing what happens on screen, it looks at a set of reference photos and builds a description that explicitly ties specific visual details to those pictures. It cleverly ignores irrelevant reference images that do not match the video content, ensuring every mention is accurate. This makes it incredibly useful for checking if a caption actually matches the visuals. You can even train the model yourself to get even better results. It is a smart step forward for making video descriptions truly factual and grounded.

🆔 @hackernewsgithubprojects

📦 sonhm3029/freqortho-sr

FreqOrtho-SR

FreqOrtho-SR is a one-step diffusion framework for real-world image super-resolution that fixes the common problem of blurry details by using two specialized experts. It works by routing low-quality inputs to pixel-level experts based on frequency analysis, ensuring sharp restoration. Then it separates the visual fidelity from artistic details by projecting gradients onto independent spaces, so the model doesn't confuse structure with style. This orthogonal expert learning approach means you get a single forward pass that delivers both accurate pixels and rich perceptual quality without the usual artifacts.

🆔 @hackernewsgithubprojects

📦 jasper-yan/agentstream

AgentStream: Testing AI That Learns On The Fly

AgentStream is the research framework that finally tests how well self-evolving AI agents perform when tasks come in a continuous stream rather than in isolated, one-off tests. The repository bundles the Exgentic evaluation engine to orchestrate benchmarks like customer support simulations and software debugging into sequential or interleaved flows. This allows researchers to see if an AI actually improves from its own mistakes over time, or if it just memorizes a single problem. It is a crucial step toward understanding if these agents can handle the messy, real world.

🆔 @hackernewsgithubprojects

📦 kbyrski/flare

FlaRe

FlaRe is a mysterious project that hints at something called Floating Radiance Networks, though the code itself is barely there right now. The repository contains almost nothing beyond a single readme file and a promise that it is launching soon. It appears to be a placeholder or an early teaser for a future network-based tool, but since there is no actual source code or functional software to test, it does not yet let you do anything concrete. It is essentially a digital placeholder waiting for the real development to begin, leaving viewers curious about what might eventually emerge from this sparse collection of files.

🆔 @hackernewsgithubprojects

📦 amelieheinrich/agfx

Agfx Cross Platform Graphics Library

Build and ship beautiful high-performance games across multiple operating systems using a single, unified graphics library. Designed specifically to help indie developers target Direct Three D Twelve, Metal Four, and Vulkan without drowning in platform-specific code, agfx is a lightweight wrapper that keeps things incredibly simple. Instead of dealing with complex descriptor sets or root signatures, it uses a bindless first approach where you reach GPU resources using plain integer handles. You get immediate access to modern features like inline raytracing, mesh shaders, and GPU-driven rendering while writing your shaders just once.

📰 https://news.ycombinator.com/item?id=49304558

🆔 @hackernewsgithubprojects