56 subscribers
7.29K videos
7.89K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ caviraoss/akashic

Akashic: Your Own Live Intelligence Map

Connect aircraft, satellites, and global weather to a single live map without touching a single API key. Akashic solves the headache of fragmented data tools by letting you self-host a powerful intelligence workspace that runs on public feeds alone. The standout feature is its ability to layer live air traffic, seismic events, and strategic infrastructure onto one interactive globe for real-time correlation. You don't just watch a dashboard; you actively explore connections between disparate data points directly on the map. It is built for privacy and simplicity, requiring no external accounts or complex environment setups.

πŸ“° https://news.ycombinator.com/item?id=48966939

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

Prolly: The Map That Never Loses Data

Prolly gives your app a superpower: it creates snapshots of your data that are completely safe to copy, edit, and delete without ever changing the original. Think of it as a digital time machine for your key-value data. Normally, if you want to try a change without breaking what's there, you have to carefully copy everything or risk losing track of where you started. Prolly uses a clever structure called a prolly tree to make those copies nearly free. You can branch off your main data, make tons of changes, and merge them back in later.

πŸ“° https://news.ycombinator.com/item?id=49325458

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ ccch1mneyyy/working-activity

Make Your AI Agent Talk Back With working-activity

working-activity is the status-line extension that turns your silent coding agent into a chatty companion. Instead of staring at a boring spinning wheel while your AI thinks, you get real-time updates on exactly what it is doing, wrapped in playful, human-like text. It tracks actual tool progress, shows you when the model is stuck, and even drops in rare, colorful visual easter eggs to keep things fun. Whether you are using the Pi CLI or DeepSeek Harness, this project makes the wait for your code to compile feel alive instead of empty.

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

Claude Plugins: The App Store for AI Coding Agents

Over sixty thousand distinct AI skills are currently scattered across public repositories, making it nearly impossible for developers to find the right tools for their specific coding tasks. The project known as Claude Plugins solves this fragmentation by acting as a unified registry and command line interface that automatically indexes these resources from GitHub. It allows you to search, install, and manage extensions for major AI coding assistants like Claude Code, Cursor, and Windsurf with a single simple command. The system even includes a special meta skill that lets your AI agent autonomously find and install new capabilities on its own before starting a task.

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

YunX: The Android App That Cracks Cloud Share Links

Paste a cloud share link and watch it transform into a direct download. YunX is an Android app built to bypass the annoying hurdles of major Chinese cloud drive services like Baidu and Quark. Instead of forcing you to install bloatware just to grab a file, it parses the share URL, extracts the real file location, and lets you download it directly on your device. The coolest part? It uses a built-in browser to handle the login for you. You just sign in once inside the app, and it automatically captures the necessary cookies to keep you connected without any complicated coding.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ brenpoly/be-more-agent

Be More Agent: The Offline AI Robot for Your Pi

Be More Agent is the offline AI companion that turns a Raspberry Pi into a fully private, conversational robot. Instead of sending your voice data to the cloud, it listens, thinks, and speaks entirely on your own hardware, keeping every interaction local and secure. The project stands out because it acts as a blank canvas, letting you swap in custom face animations and sound effects to create a unique character with a personality of your own. It handles speech recognition, reasoning, and even visual perception without needing an internet connection, making it a fascinating tool for building a personal assistant that respects your privacy.

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

Double-Click DeepSeek: No Setup Needed

Run a full AI agent on your desktop without touching a single terminal. DSH Desktop bundles the entire DeepSeek Harness runtime and Node environment into one neat package, meaning you can double-click a file and be chatting in seconds. It skips the usual headache of installing dependencies or configuring ports, turning a complex command-line tool into a simple, native window that even lives in your system tray. The best part is how it handles your workflow; it includes a tiny whale pet that sits on your desktop to keep you company while your tasks run.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ webpro-nl/unbash

unbash: The Fast Bash Parser

Inspecting bash scripts without running them sounds risky, but unbash changes that. This TypeScript tool parses shell commands instantly, giving you a clear, typed map of the structure without executing a single line. It is incredibly fast, handling massive files at speeds that make older parsers look like they are stuck in the past. The real magic is how it handles nested commands, letting you see exactly where variables and subshells live so you can audit your code safely. It even recovers from broken input, so your tools never crash on bad data.

πŸ“° https://news.ycombinator.com/item?id=47333545

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

Jaz: Your AI Never Sleeps

Jaz lets your coding agents run loops overnight on your own machine. It is a personal AI setup that connects to Codex, Claude, and other tools so they can keep working while you sleep. The software uses a client and server split, meaning the heavy lifting happens on a backend you control. You can plug in your existing subscriptions, so you are not paying extra for a new platform. It adds memory that sticks around and lets you push code directly to git. The result is a powerful, always on assistant that lives on hardware you own, not in some closed cloud service.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ small-tailqwq/dsh-deep-whale

Deep-Sea Maid Skins for DeepSeek

Your DeepSeek interface can now look like a deep-sea maid cafe, complete with chibi whale characters and lace accents. The DSH Deep Whale repository provides a visual skin that overlays your existing app without altering any code or performance. It adds dual maid backdrops and decorative frames, automatically switching between light and dark modes to match your preferences. All artwork is embedded directly into the package, so it works instantly without needing external servers. This project proves that even serious developer tools can have personality, letting you enjoy a cozy, anime-inspired workspace while keeping your code clean.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ bigattichouse/llama-optimize

llama-optimize

llama-optimize uses a statistical trick to find your GPU’s best settings in hours instead of days. It runs a smart, two-stage experiment on your machine to test only the most important combinations of knobs. It automatically detects your hardware, runs a small set of benchmarks, and hands you a copy-paste command for the fastest setup that still fits your memory. It even tells you the exact speed trade-off between maximum speed and maximum context length. You get a ready-to-use command for the specific way you run your model, like for multiple users or long-prompt agents. No more guessing which settings work best for your specific hardware and model.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ thaakeno/comfyui-minimax-h3-studio

MiniMax H3 Studio: The Secret Weapon for AI Image Editing

Turn MiniMax H3 into a polished image workflow for ComfyUI with MiniMax H3 Studio. Instead of wrestling with complex model routing and reference conditioning, this tool gives you a single, intuitive interface to generate, edit, and refine stills. You can drop in up to nine reference images, assign specific roles like lighting or pose to each, and let the system handle the heavy lifting. The standout feature is Face Refine, which detects small or distant faces in your final output, rerenders them at a higher resolution, and blends them back in for crisp, detailed results. It even includes built-in benchmarking to compare speeds and quality.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ aitabby/dockyard-dsh

One App for Every AI Coding Account

Dockyard DSH packs a native macOS app that lets you manage multiple AI coding accounts in one place, eliminating the need to switch between different browser tabs or login sessions. It runs locally on your Mac, using a secure vault to store your credentials and connecting directly to various AI providers like Claude and Codex. The real magic is its account pooling feature, which automatically cycles through your available accounts to avoid hitting rate limits during long coding sessions. It’s a clean, single-window solution that keeps your workflow focused and your AI access uninterrupted.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ l5yth/potato-mesh

PotatoMesh: Your Community's LoRa Mesh Map

PotatoMesh is the local dashboard that turns scattered radio signals into a live community map. It takes raw LoRa traffic from your neighborhood and displays it as a real-time map showing where people are, who they are talking to, and how the network is connected, without relying on the internet or centralized servers. The project automatically links with other local groups, creating a wider network of community run nodes. It is perfect for seeing how local off-grid communication actually works in your own area.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ roadmaus/comfyui-minimax-creator

One Node, Every Shot: MiniMax Creator

Create full video clips with synchronized sound using a single, self-contained node in ComfyUI. The MiniMax Creator eliminates the complex wiring of traditional workflows by handling everything from prompt writing to final rendering in one place. You can even extend that single node into a multi-shot timeline, letting you build longer narratives where scenes flow together with continuous audio and visual continuity. It runs entirely on local open weights, so your creative process stays private without needing API keys or cloud uploads. The node intelligently manages references, faces, and sampling settings, allowing you to generate high-quality, multi-shot videos locally.

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

HarnessRouter: Run AI Agents Locally

HarnessRouter puts professional AI coding agents directly onto your own hardware, letting you run tools like Codex and Claude Code without any cloud account. It works by spinning up a single Docker container that gives these agents a real workspace with terminal access and file systems, not just a chat window. You plug in your existing API keys, paste your prompts, and watch the agent write code, run commands, and debug errors live in a browser console. The project stands out because it implements an open standard for how these agents talk, meaning you are not locked into one vendor’s proprietary system.

πŸ“° https://news.ycombinator.com/item?id=49335595

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

Simulating Real Human Hands with Physics

Human hands are soft, yet physics engines typically treat them as stiff, brittle objects that shatter on impact. Manosim solves this by converting detailed digital hand models into a format that rigid-body simulators can actually understand. The project takes a standard hand model and rebuilds it as a physical object with realistic weight, inertia, and smooth collision surfaces. This allows researchers to test how robots might interact with human hands using accurate physics, rather than simple geometric shapes. It bridges the gap between digital animation and physical reality. You get a realistic hand you can actually simulate, not just look at.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ tiger3807861189/deepseek-v4-j-space-capability-realization-report

DeepSeek V4 J-Space Capability Realization Report

DeepSeek V4 is so powerful that its main problem is actually its own unpredictability. This new report from a developer named Tiger proves that a tool called J-Space can fix this by keeping the model focused without changing its core brain. Think of it like giving a brilliant but distracted expert a strict checklist and a memory aid. By organizing how the model thinks, checks its work, and remembers where it left off, the setup helps it finish complex coding and reasoning tasks without losing the plot. The results show it beats several top-tier competitors on tough benchmarks.

πŸ“° https://news.ycombinator.com/item?id=49336380

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

Moli: The Browser That Saves AI Ten Megabytes

Moli is a headless browser built in Rust that runs on just seventy-three megabytes of memory while matching Chrome’s speed, solving a huge problem for AI agents. Instead of constantly rendering the visual world, it treats the page structure as the source of truth and only calculates visuals when you truly need a screenshot. This means your AI can crawl, search, and automate tasks in a fraction of the cost without the heavy overhead of a standard browser. It is a complete runtime that fits in your pocket, making it the perfect tool for anyone building automated web workflows that need to be fast and efficient.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ ai-evals-course/evals-skills

How to Find AI Mistakes with Evals Skills

Evals Skills is the agent guide that finally turns raw AI outputs into actionable error insights. It stops you from guessing what went wrong and instead builds a custom review tool to help you find it. The standout feature is the error discovery mode, where you point an AI agent at your data and it designs a visual interface to help you spot mistakes. As you review samples and leave notes, the agent organizes your feedback into failure categories and suggests new items to review. This turns a chaotic manual process into a structured workflow that catches subtle issues you would likely miss alone.

πŸ†” @hackernewsgithubprojects