📦 magicrew/doc7

doc7

You can now transform any complex PDF or messy screenshot into clean, AI-ready Markdown using your own local vision model, with absolutely zero document parsing fees. A clever tool called doc7 bypasses traditional, rigid OCR engines entirely. Instead, it takes your document, renders the pages, and feeds them directly to a local model running in Ollama or LM Studio to reconstruct everything. It can perfectly recover complex mathematical formulas, diagram relationships, and even visual chart data from flat images. It is incredibly easy to run right from your terminal, keeping all your sensitive data completely private. Download doc7 today and unlock the power of local document understanding.

🆔 @hackernewsgithubprojects

📦 worldbench/awesome-agentic-world-model

Awesome Agentic World Model: A Map for Smarter AI

Explore how artificial intelligence learns to predict the future by checking out this curated collection of research on agentic world modeling. It maps out the shift from passive simulations to interactive environments where AI agents can test plans, learn from mistakes, and improve continuously without risking real-world damage. Think of it as a cheat code for training smarter robots and software assistants by letting them practice in safe, virtual simulations. It organizes dozens of papers into a clear guide, showing how machines can imagine consequences before acting.

🆔 @hackernewsgithubprojects

📦 kenton-gmi/sakura-crossing

Sakura Crossing: Anime World From Code

Walk through a fully 3D Japanese neighborhood that looks exactly like a hand-painted anime background, all created without a single image file. This project uses clever rendering tricks to turn depth data into crisp ink lines and flat, colorful shading, making a real-time world feel like a studio production. You can explore streets, shrines, and a railway loop on a tiny planet, even hopping onto an electric bike to ride around. It is a stunning example of how code can mimic art.

🆔 @hackernewsgithubprojects

📦 chenchishui/futurebridge-opd

FutureBridge-OPD: Teaching AI to Look Before It Leaps

FutureBridge-OPD solves a nagging problem in AI learning where small mistakes snowball into big failures. Instead of just copying a teacher’s final answer, this tool makes the student look ahead. It spots a confusing moment in a task, tries a different path suggested by the teacher, and then checks if that new path actually works better. If it does, the student keeps it. This simple validation step keeps the learner on track and prevents it from drifting into wrong territory. It is a clever way to make self-learning models much more reliable without needing endless trial and error.

🆔 @hackernewsgithubprojects

📦 oxpig/nispo

NISPO: Turn Molecules into Names

Nispo turns molecular blueprints into perfectly formatted chemical names that always reverse back to the original structure. Instead of guessing how to name complex compounds, you just feed it a simple string representation and get back a valid IUPAC name every time. This tool solves the headache of chemical nomenclature by using an AI-generated codebase that obsessively tests every output against a verification engine to ensure a perfect round trip. It is genuinely cool because it handles massive datasets with nearly perfect accuracy, turning a tedious manual task into a reliable automated process.

🆔 @hackernewsgithubprojects

📦 avencera/speakrs

Speakrs: Rust Speaker Diarization

On a Mac laptop, this project called speakrs listens to a recording and tells you exactly who is speaking, running nearly five hundred times faster than standard tools without losing accuracy. It is a complete Rust library that breaks down audio into individual voices, identifying when each person talks and who they are. Instead of relying on slow Python scripts, it uses your computer’s native hardware to process sound instantly. This means developers and creators can add professional speech-to-text features to their apps without the usual speed bumps or heavy setup. It turns complex audio analysis into a simple, fast task anyone can use.

📰 https://news.ycombinator.com/item?id=48282551

🆔 @hackernewsgithubprojects

📦 cohesity/scalablerag

ScalableRAG: AI That Answers Questions Without Pre-Processing

ScalableRAG is the question answering system that finally lets you query massive libraries of documents without spending days pre-processing them. Traditional tools usually require you to build complex databases or vector indexes before you can ask anything, which is expensive and slow. This project flips that script by offering a zero-ingestion mode that skips all that heavy lifting entirely. Instead of searching static indexes, it gives the AI a workspace of dynamic sets to explore, filter, and analyze right as you ask. It mimics how a human would logically group and count information across files, matching or beating far more complex systems.

🆔 @hackernewsgithubprojects

📦 ielab/skim-search-agent

SkimSearchAgent: Deep Research for Your Data

SkimSearchAgent lets you build intelligent research assistants that dig through your own document collections to answer complex questions without you writing code. Instead of guessing answers from a static database, this tool gives an AI model a loop where it can actively search, inspect results, and fetch specific sections of your documents to piece together accurate answers. It is fascinating because it separates every part of the process, meaning you can swap out different search methods, document structures, or even the AI brain driving the logic without breaking the whole system.

🆔 @hackernewsgithubprojects

📦 petroni-lab/librarian

AI Librarian: Natural Questions to Scientific Evidence

Ask a messy biology question like whether metformin extends lifespan and get back the exact sentences that answer it, not just a list of papers. This project acts as a smart librarian for artificial intelligence, taking your natural language query and turning it into a series of precise search commands across the Europe PMC database. It doesn't just dump results; it reads through the actual full text of open-access studies, filters out the noise, and extracts only the specific evidence snippets that matter. Think of it as a research assistant that skips the fluff and hands you the hard proof.

🆔 @hackernewsgithubprojects

📦 198808xc/dramasr-lrm

DramaSR-LRM: AI That Guesses Who Is Talking in TV Dramas

DramaSR-LRM turns large language models into sharp listeners that figure out who is speaking in long, messy TV dramas. Traditional speech recognition fails when voices change or characters disappear off-screen. This project solves that by training a model to think before it speaks. Instead of guessing instantly, the AI calls tools like audio comparison and character relationship maps to build a solid argument. It learns to weave together visual clues and voice patterns, catching subtle shifts that standard software misses. The result is a system that actually understands context, not just sound. It is a clever way to make AI pay attention to the story, not just the audio.

🆔 @hackernewsgithubprojects

📦 apphane-dev/nehir

Nehir: Scrolling Window Manager for macOS

Nehir lets you manage your macOS desktop using a horizontal scrolling layout that feels like a river of windows. Instead of stacking apps on top of each other or jumping between static workspaces, Nehir arranges your open windows into columns that slide left and right across your screen. It brings the popular Niri workflow to Mac, meaning you get smooth, animated transitions between apps without losing context. You can customize hotkeys, app rules, and monitor setups with simple text files that update instantly. It handles multiple displays well, keeps your dock out of the way, and even lets you trace exactly what caused a glitch if something goes wrong.

📰 https://news.ycombinator.com/item?id=49194123

🆔 @hackernewsgithubprojects

📦 raven-july/cfpo

CFPO: Smarter Multimodal Reasoning

CFPO is a counterfactual reinforcement learning framework that finally forces large vision-language models to actually look at images instead of guessing from text. Standard AI methods often let models cheat by relying on linguistic shortcuts rather than visual evidence, and CFPO solves this by testing whether the prediction changes when critical visual cues are suppressed. It builds a counterfactual path that blocks high-saliency visual signals, then rewards the model only if its reasoning genuinely depends on the image rather than blind language patterns. This approach consistently beats standard training baselines on math and logic benchmarks without needing external reward models.

🆔 @hackernewsgithubprojects

📦 larryvrh/comfyui-minimax-h3-turbo

ComfyUI-MiniMax-H3-Turbo

Create synced video and audio in just four generation steps using the ComfyUI-MiniMax-H3-Turbo project, which transforms how you handle multimedia generation. The repository provides a custom sampler and LoRA loader that bypass the usual twenty-step process, cutting generation time to a fraction of what it normally takes. It solves the tricky problem of audio distortion that usually wreals havoc when you rush video models, ensuring your sound stays crisp even at ultra-low step counts. By dropping two simple nodes into your existing workflow, you get fast results without complex tweaks. This is a neat trick for anyone who wants to experiment with fast-paced multimedia creation without waiting around.

🆔 @hackernewsgithubprojects

📦 aaddrick/attention-control

Attention Control: Air Traffic Discipline for AI

Attention Control forces coding agents to talk like air traffic controllers, stripping away the usual fluff so you get immediate, actionable instructions. It treats your attention like a pilot’s focus, demanding that every response lead with the next executable command instead of a polite preamble. This style was built for readers with ADHD but helps anyone drowning in context switches, by replacing vague suggestions with concrete steps and hard deadlines. You stop guessing and start running code. If your AI assistant is currently writing essays, this style forces it to get out of the way and let you work. It is a simple shift that makes complex help actually usable.

🆔 @hackernewsgithubprojects

📦 beatapi/awesome-minimax-h3-prompts

Awesome Minimax H3 Prompts: Curated Video Generation Library

This repository is a curated gallery of over one hundred ready-to-use text prompts designed specifically for the MiniMax H3 video generation model, turning simple descriptions into playable video clips. Instead of just listing text, it provides full production details including camera movement, lighting styles, and character interactions, covering diverse genres like action, anime, and product demos. It solves the problem of trial-and-error prompting by offering tested examples with credited sources, allowing creators to quickly generate cinematic sequences, commercials, or viral shorts without guessing the right technical phrasing.

🆔 @hackernewsgithubprojects

📦 1038lab/comfyui-minimax-h3-promptor

Create Cinema Prompts for MiniMax H3

Create cinema-quality video prompts automatically by feeding images into ComfyUI. This tool splits the work into two steps. First, it analyzes your pictures using any AI model you want, like OpenAI or Claude. It extracts details about lighting, characters, and mood, then sends that text report to a second node. That second node takes your creative idea and the visual report to write the perfect prompt. It even guesses whether you want a text-to-video or image-to-video result based on your inputs. You get precise, professional results without paying extra for the AI to look at your images twice.

🆔 @hackernewsgithubprojects

📦 guillermolg00/morphicons

Morphicons: Universal Icon Morphing

Morphicons lets any icon morph into any other using spring physics. Instead of manually declaring rotations, it calculates the optimal path so arrows rotate naturally instead of shrinking. The library handles strokes from major icon sets with zero dependencies and a tiny file size. It works seamlessly in React, Vue, Svelte, and React Native. State lives outside while the component handles the animation details. You get clean server rendering and accessibility defaults out of the box. It solves the messy transition problem with pure math. The core never touches the DOM, keeping everything fast. Even interruptions feel smooth thanks to velocity preservation.

🆔 @hackernewsgithubprojects

📦 frozenpepper/deepseek-and-destroy

DeepSeek and Destroy: Autonomous Coding Agent

Give a coding agent a complete plan, and it executes the entire multi-phase project without stopping to ask for your permission after every single task. DeepSeek and Destroy is a tool that splits work between a smart boss and cheap workers. The boss handles big decisions, while inexpensive agents do the heavy lifting, write code, review each other, and fix bugs automatically. It runs in a strict loop of implement, review, repair, and verify until the job is fully done. This setup saves money and time because the expensive AI only steps in for major choices, leaving the repetitive grinding to faster, cheaper models.

🆔 @hackernewsgithubprojects

📦 openclaw/ffmpeg-wasm

ffmpeg-wasm: Media Processing in Your Browser

ffmpeg-wasm is the browser-native media processor that turns your web app into a full video studio without downloading heavy native binaries. Instead of relying on massive server-side installs, this project compiles the essential parts of FFmpeg into a tiny, lightweight WebAssembly package that runs right inside your browser or Node environment. You can easily extract audio, grab thumbnails, or reformat videos using simple commands that feel just like working with the traditional command-line tools. It handles the tricky heavy lifting of video conversion locally, keeping things fast and private while avoiding the need for complex infrastructure setups.

🆔 @hackernewsgithubprojects

📦 mintdotgg/mint-playground

Mint Playground: Open-Source 3D Experiences

Mint Playground is the open-source collection that turns simple web code into stunning three-dimensional worlds you can actually play with. Instead of just reading about cool visuals, this repository lets you grab ready-made experiences like arcade basketball games, fantasy action adventures, or interactive furniture showrooms and run them instantly in your browser. It solves the boring problem of building complex 3D sites from scratch by providing polished templates that work out of the box. This is useful because you get to see exactly how developers create immersive interactive media without needing to reinvent the wheel every time.

🆔 @hackernewsgithubprojects

📦 tencent/tencentdb-agent-memory

TencentDB Agent Memory

TencentDB Agent Memory is the team library that turns past work into reusable brainpower for artificial intelligence assistants. Most tools just store chat logs, but this system actually learns from your history to build a living skill library. It scans your old conversations and code to extract reusable instructions, structured knowledge, and code maps, then packages them into a portable save file. You can hand this file to any assistant, and it instantly understands your project context, preferences, and past decisions without being retrained from scratch.

🆔 @hackernewsgithubprojects