57 subscribers
7.3K videos
7.9K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ hkuds/catchme

CatchMe: Make Your AI Agents Truly Personal

CatchMe is the local privacy tool that turns your entire digital life into a searchable memory for your AI agents. It silently records everything you do on your computer from mouse clicks to open windows and organizes it all into a smart, hierarchical tree of events. Instead of relying on heavy vector databases, it uses a lightweight AI to summarize your day into readable chunks that your favorite coding assistant or chatbot can instantly query. You can ask questions like what file you edited last week and get a precise answer backed by your actual screen history.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ agentplugins/agent-plugins-spec

Agent Plugins: The Standard for AI Skills

Agent Plugins is the open standard that finally lets you package AI skills as portable, reusable plugins. Think of it as a simple zip file containing a tiny manifest and some instruction files that any compatible AI agent can read and use, regardless of whether it comes from Cursor, OpenAI, or Microsoft. Instead of writing custom code for every new tool, you just drop a folder into your project. The agent reads a basic JSON file and a markdown instruction to understand exactly what the plugin can do, like greeting a user or fetching weather data. This means one plugin works everywhere, saving you from rewriting logic for each platform.

πŸ“° https://news.ycombinator.com/item?id=49201435

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ nduckmink/arkon

Arkon: Turn Company Docs into a Smart Wiki

Arkon lets teams turn messy internal documents into a smart, searchable wiki that connects directly to artificial intelligence tools. Most people dump files into chatbots and lose context, but this project compiles your policy manuals and guides into a structured, interlinked knowledge base. The real magic happens in its pipeline, which drafts new wiki pages from your sources and then waits for a human to review the plan before actually writing anything. This prevents accidental data loss and keeps the information accurate.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 3xpyth0n/ideon

Ideon: Your Infinite Project Canvas

Organize your scattered notes, files, and tasks on one infinite canvas. Ideon replaces the chaos of switching between dozens of tools with a single visual workspace where everything lives together. You can drag and drop notes, link to repositories, and manage to-do lists right on the whiteboard. The real magic happens with automations: set up rules to trigger actions or alerts based on your project activity, all without writing complex scripts. It keeps your entire workflow visible and connected, turning a messy collection of tabs into a clear, interactive map of your work.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ google-gemma/gemma-translator

Gemma Translator

Turn a Raspberry Pi into a pocket-sized voice translator that works completely offline. You hold a key to record a phrase, and the device instantly listens, translates it into the other person’s language, and speaks it back in real time. It runs the heavy lifting locally using Gemma and speech models, so there is no cloud needed and no internet connection required. The interface looks like a retro terminal, designed specifically for small screens where two people can sit face to face and chat across different languages. It is a clever, self-contained hack for breaking down language barriers anywhere.

πŸ“° https://news.ycombinator.com/item?id=49202123

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ webfuse-com/awesome-claude

Awesome Claude: The Ultimate Guide Collection

Awesome Claude is a curated collection of everything related to the Claude AI assistant. It gathers official Anthropic resources, developer tools, community guides, and helpful extensions into one easy-to-find list. Instead of hunting across the web for coding tips or model comparisons, you get a single, organized directory covering everything from beginner courses to advanced coding agents. It is a simple, free resource for anyone wanting to learn how to work better with Claude. Check it out if you want to speed up your workflow today.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ pinchtodebug/everythingquicksearch

Everything Quick Search

Everything Quick Search is the Windows launcher that finally bridges the gap between file hunting and app launching, turning your desktop into one unified search bar. Instead of juggling separate tools for finding files and opening programs, it taps into the lightning-fast Everything engine to index your entire drive and present results in a single, clean window. You can toggle regex filtering to hunt down complex file patterns, navigate with simple keyboard shortcuts, and instantly open whatever you need without leaving the search interface. It is a brilliant way to reclaim your workflow, making file management as fast and fluid as launching an app.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ guqiong96/lvllm

LvLLM Runs Huge AI Models on Your CPU

LvLLM lets you run massive AI models that usually need expensive graphics cards by cleverly using your computer’s regular memory and processor. It splits the workload so the graphics card handles some tasks while the central processor handles the rest. This hybrid approach means you can run huge language models without needing a room full of GPUs. It is a special tweak for the popular vLLM engine that balances the load across your hardware. If you are running out of graphics memory, this project is a clever way to keep your AI running smoothly on the hardware you already own.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ gundulabs/gaze

Gaze: Face Unlock for Linux

Gaze is the facial recognition system that finally lets you log into Linux with a glance. Most Linux users are stuck typing passwords or relying on fingerprints, but this tool turns your standard webcam into a secure biometric scanner. It runs entirely on your machine, capturing your face, building a local model, and verifying your identity without sending data to the cloud. The coolest part is how quietly it works in the background. You can simply look at your screen when you wake your laptop, and the system checks your face in milliseconds. If it matches, your session unlocks automatically.

πŸ“° https://news.ycombinator.com/item?id=49202832

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ reporails/cli

cli

cli is the diagnostic tool that finally grades your AI agent’s instruction manuals. Most developers just dump a massive instructions file and hope for the best, but this tool actually reads those rules and spots the confusing bits, contradictions, and missing details before they cause chaos. It checks everything against over a hundred different guidelines tailored for agents like Claude or Cursor, giving you a simple quality score and clear fixes. You run it, see what is broken, tweak your docs, and watch your score climb. It turns vague direction into clear, reliable code that agents can actually follow. Stop guessing and start building better instructions today.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 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.

πŸ“° https://news.ycombinator.com/item?id=49194719

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 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.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 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.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 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.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 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.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 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.

πŸ“° https://news.ycombinator.com/item?id=49117510

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 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.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 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.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 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.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 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.

πŸ†” @hackernewsgithubprojects