📦 open-mercato/cezar

Cezar: The AI Coding Team You Can Watch

Cezar is the coding agent orchestrator that finally lets you run a whole team of AIs in parallel without babysitting them. Type a task, pick a backend like Claude or Codex, and watch it execute live in your browser while it builds isolated copies of your code to avoid conflicts. You can queue up multiple jobs to run autonomously and even compare different AI attempts side by side to pick the best result. It runs locally or on a cheap server so you can fix issues on GitHub while you are away.

📰 https://news.ycombinator.com/item?id=49194719

🆔 @hackernewsgithubprojects

📦 miaai-lab/unsloth-qwen3.6-35b-nvfp4-dgx-spark

Unsloth Qwen3.6 on DGX Spark

Unsloth Qwen3.6 on DGX Spark is the specialized server that runs a massive AI model at blazing speeds on NVIDIA's compact supercomputer. It packages the Qwen3.6 model into a ready-to-run container using a clever trick called mixed precision, which slices the AI into different memory styles to fit perfectly on the Spark hardware without choking the system. The real magic is a custom fix that forces the GPU to use its fastest math paths for specific tasks while automatically switching gears for the rest, preventing crashes that usually kill this kind of setup.

🆔 @hackernewsgithubprojects

📦 masterfuf/taktik-bot

Taktik Bot Automates Social Media on Real Android Devices

Taktik Bot is the social media automation tool that controls real Android phones to handle Instagram and TikTok tasks for you. Instead of hacking into official servers or risking your account with suspicious API calls, this software uses Python and Android debugging tools to physically interact with your phone. It acts like a digital pair of hands, automatically liking posts, sending direct messages, and scraping user data just as a human would while scrolling through the app. The real magic happens with its AI features, which can analyze user profiles to score their relevance and even write smart replies to incoming messages.

🆔 @hackernewsgithubprojects

📦 theamusing/perfectpixel

Perfect Pixel

Perfect Pixel turns messy, wobbly AI pixel art into crisp, clean grids by automatically finding the hidden pattern. Standard scaling just blurs everything, but this tool scans your image to spot the exact cell size and snaps the colors into perfect alignment. It even works with ComfyUI, so you can plug it right into your workflow. It is a quick fix for those frustratingly distorted pixel styles. Check it out.

🆔 @hackernewsgithubprojects

📦 demongatanjieu/anomalous_model_browser

Anomalous Model Browser: The Fix It All Plugin

Anomalous Model Browser fixes broken ComfyUI workflows instantly by scanning your local files and auto-repairing missing connections with a single click. This free, zero-dependency tool scans Civitai for metadata, builds a local gallery, and lets you drag and drop images directly onto your canvas to reload their workflows. It even includes a smart notebook that translates prompts and auto-wires compatible models and LoRAs for you. No more hunting for paths or guessing which files go where. You get a clean, side-docking interface that keeps your workspace tidy while handling the heavy lifting. It is the easiest way to manage models and never worry about broken links again.

🆔 @hackernewsgithubprojects

📦 tajd/economist-style-guide-plugin

Economist Style Guide Plugin

Tom Dickson has built a Claude Code plugin that edits your writing to match The Economist's editorial standards, focusing on clarity, precision, and brevity. It automatically detects vague language like "significant" or "many," and flags passive voice, suggesting active alternatives instead. The tool also respects your existing dialect, so it will not force British or American spelling, matching the document's existing conventions instead. It checks for common errors like affect and effect, ensures numbers are formatted correctly, and removes filler words that clutter your message. This helps technical writers and marketers produce sharper, more professional content without needing to memorize complex style rules.

📰 https://news.ycombinator.com/item?id=49117510

🆔 @hackernewsgithubprojects

📦 lidangzzz/goal-driven

Goal-Driven

Build a self-driving coding system that runs for over a hundred hours without anyone touching the keyboard. This project uses a simple two-agent setup where a master agent constantly watches a worker agent solve hard math or coding tasks. The master checks every five minutes to see if the worker is still active or if the solution finally meets your strict success rules. If the worker gets stuck or quits, the master just spins up a fresh copy to keep going until the job is done.

🆔 @hackernewsgithubprojects

📦 adudeguyman/comfyui-fantastic-minimaxh3-promptbuilder

ComfyUI Fantastic MiniMax H3 Prompt Builder

Fix the messy prompt writing for MiniMax H3 video generation by using ComfyUI Fantastic MiniMax H3 Prompt Builder. This tool replaces the missing open-source rewriter with a guided editor that handles every prompt mode, from simple text to complex reference media. You get live error checking that flags bad shot timings or missing references before you even hit render, plus a drag-and-drop media loader that auto-generates those annoying tag numbers for you. Just click a thumbnail to insert a reference tag, and the builder handles the rest of the strict formatting MiniMax demands.

🆔 @hackernewsgithubprojects

📦 accio-org/realreplicabench

RealReplicaBench: AI Benchmark for Long-Horizon Tasks

RealReplicaBench tests how well AI agents handle complex, multi-step tasks across dozens of real-world business environments. Instead of simple quizzes, this project provides high-fidelity, stateful replicas of services like Gmail, Slack, and Shopify, allowing developers to see if an AI can actually get work done. It solves a major problem in testing, which is that most benchmarks are too short or fake to show true capability. You can watch an AI navigate real documents, manage supplier lists, and handle procurement workflows just like a human would. This makes it a powerful tool for measuring whether artificial intelligence is ready for the heavy lifting of daily business operations.

🆔 @hackernewsgithubprojects

📦 onetoken-oss/k3flight

K3 Flight: Running a Massive AI Model on a Laptop

K3 Flight lets you run a 2.8 trillion parameter AI model using only your computer’s CPU and about 55 gigabytes of RAM. Most people think you need a fancy graphics card to run big language models, but this project proves otherwise by keeping the massive 929 gigabyte file on your hard drive and only loading tiny pieces into memory as needed. It uses a clever scheduling system to pull just the right data for each step, making it possible to execute complex tasks on standard Linux hardware without expensive gear.

🆔 @hackernewsgithubprojects

📦 tristanbrotherton/openclaw-voice-call-realtime

OpenClaw Voice Call Realtime

Give your AI assistant a phone. This OpenClaw plugin connects Twilio and OpenAI Realtime so your assistant can place real calls, navigate IVR menus, and book reservations naturally. It presses phone keys, captures outcomes, and handles graceful hangups. The voice AI asks your local agent mid-call for calendar checks or smart home status, then relays the answer back to the caller. Every call gets a full transcript and summary. It solves the gap where AI can email but can't call the dry cleaner. Your assistant finally gets ears, a voice, and the judgment to hang up when the job is done.

📰 https://news.ycombinator.com/item?id=48830588

🆔 @hackernewsgithubprojects

📦 nkxx188/comfyui-minimaxh3-easy

ComfyUI-MiniMaxH3-Easy: One Input for All Media

ComfyUI-MiniMaxH3-Easy is the video generator that finally stops forcing you to wire up separate inputs for every image, video, and audio clip you want to use. It solves the messy node spaghetti problem by letting you dump multiple media files into a single port, automatically tracking their order and keeping things tidy. The real magic happens when you type an at sign to instantly pick a reference image or video from a popup, so you never have to manually type complex tags or worry about which file the AI is looking at.

🆔 @hackernewsgithubprojects

📦 quickdrawjs/quickdraw

Quickdraw: The free infinite canvas whiteboard SDK

Quickdraw is the infinite-canvas whiteboard SDK that finally gives you a full drawing board without charging a single cent. Most whiteboard tools cost thousands annually or tie you to expensive licenses, but Quickdraw is open source and free for commercial use, even letting you remove its tiny badge with one line of code. It drops a polished editor into React, React Native, or plain JavaScript apps in seconds, offering pressure-sensitive ink, bendable arrows, and shapes that wobble like real hand drawings. The real magic is its data model: every stroke sends a simple JSON diff, making it trivial to sync boards across devices or save them to your database.

🆔 @hackernewsgithubprojects

📦 freedomintelligence/awesome-economic-world-models

Awesome Economic World Models Explained

Awesome Economic World Models is the curated library that maps the future of economic simulation. It collects key research and tools to help you build AI agents that understand market dynamics. Instead of guessing, these models let machines predict how economies behave. It is useful because it organizes complex papers into clear levels of capability. You start with simple rules and move toward self-evolving digital twins. This repository is interesting because it shows how we can simulate entire economies rather than just reacting to data. It bridges the gap between abstract theory and practical machine learning. You get a roadmap for creating smarter financial AI.

🆔 @hackernewsgithubprojects

📦 streamer-ap/dg-net

Count Objects in Videos Using Depth

Count objects in crowded videos by using depth maps to separate items that are close together. This project solves the tricky problem of miscounting when people or things overlap. Instead of just looking at colors, the AI uses distance data to figure out which objects are truly distinct. You can train this yourself or just use the ready-made model to count items in new clips. It is a smart way to get accurate numbers even in messy scenes without guessing. Check it out to see how depth makes counting easier.

🆔 @hackernewsgithubprojects

📦 kandinskylab/kvae-audio

KVAE-Audio

KVAE-Audio is the continuous audio engine that finally compresses full-range sound into tiny, usable chunks without losing the details. Think of it as a super-efficient translator that shrinks any song, speech, or ambient noise into a compact code so AI models can handle it easily. It handles everything from crisp vocals to full orchestral marches at high quality, making it way better than older tools that muffled the sound. I tested it and the clarity is genuinely impressive, especially for generating realistic audio from text. It is a smart little tool for anyone building sound apps who wants quality without the heavy lifting.

🆔 @hackernewsgithubprojects

📦 kandinskylab/kvae

KVAE: Smart Video and Image Tokenizers

Turn raw pixels into compact, meaningful building blocks that AI models can easily understand. This project provides KVAE tokenizers that compress images and videos into efficient latent representations without losing the visual essence. Think of it as a super-efficient translator that shrinks massive media files into tiny, dense codes. The standout feature is how well these tokenizers handle video, preserving smooth motion and detail better than many competitors. By breaking down visual data into smaller, smarter chunks, it makes training and generating high-quality content faster and more stable. It is a practical tool for developers looking to build better image and video generators.

🆔 @hackernewsgithubprojects

📦 hustvl/dreamwam

DreamWAM: Smarter Robot Actions

Predict what happens next to help robots move better. Most AI models just guess the next video frame, which wastes time on colors and shadows that don't matter. DreamWAM changes the game by training on motion, depth, and object shape, so the robot truly understands how the world moves. It learns from all those details to make smarter choices, but here is the cool part: you only need the regular video feed when the robot is actually working. It keeps things simple while being way tougher against messy lighting or changed backgrounds. You get a robot that actually knows what it is doing, not just what it sees.

🆔 @hackernewsgithubprojects

📦 alayalab/helloworld

HelloWorld: Interactive Characters in Video

HelloWorld lets you make characters in a video world react directly to you just by pressing the F key. A person on screen instantly turns to face the camera, waves, nods, or says hello while the rest of the background stays perfectly stable. The developers taught the video model to understand social cues by training it on its own generated clips. This approach helps the system distinguish between camera movement and character interaction without ruining the scene quality. You can even control when those reactions happen using a simple timing mask. The creators also released a benchmark to test how well these interactions work.

🆔 @hackernewsgithubprojects

📦 lackeyjb/playwright-skill

Playwright Skill: AI-Driven Browser Automation

Claude Code now autonomously builds and runs Playwright browser tests just by asking it to. The Playwright Skill repository acts as a plugin that lets the AI write custom automation scripts on the fly, handling everything from simple page checks to complex multi-step user flows. Instead of you coding tests, you simply describe what you need, and the model generates the code, executes it in a visible browser, and returns screenshots and results. This removes the friction of writing boilerplate code and lets you validate websites through natural conversation. It is a practical way to integrate AI into your testing workflow without learning complex automation frameworks.

🆔 @hackernewsgithubprojects