56 subscribers
7.29K videos
7.9K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
📦 j-c-zhao/structsplat

StructSplat

Imagine creating a fully detailed three-dimensional digital scene from just a few smartphone photos, without even knowing the camera settings or angles. StructSplat does exactly that by predicting three-dimensional gaussians directly from uncalibrated, sparse images. Traditional methods require precise camera positions or heavy per-scene processing to stitch images together, but this system uses a clever structured approach. It separates texture, geometry, and semantic cues to keep everything highly accurate and globally consistent. It is a massive step forward for virtual reality and game design because it lets you reconstruct rich, complex spaces instantly from a handful of casual snapshots.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 mat-mgm/kb-prolog

kb-prolog

You can now make complex statements about other statements and track their entire history like code using kb-prolog. This local-first knowledge base lets you build nested, hyper-relational graphs where a claim can easily describe another claim, such as recording that one person doubts what another person said. It combines a Prolog runtime with SQLite for storage, automatically saving and tracking version changes so you can travel back in time to see exactly how your data evolved. Plus, it features built-in file storage and an interactive graph visualizer to browse everything easily. It is a brilliant way to bring deep, logical relationships and version control to your local data.

📰 https://news.ycombinator.com/item?id=48697599

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 uw-syfi/tracelab

tracelab

Peek behind the scenes of real-world coding assistants by analyzing the exact logs they generate during development. Under the hood, tools like Claude Code emit highly complex event sequences, from tool calls to split-second timing events. This repository gives you a massive, pre-sanitized dataset of over three hundred thousand developer rounds alongside a local pipeline to clean and inspect your own assistant history. You can run prebuilt data experiments, reconstruct prompt-cache behavior, or drag logs directly into a web app to see interactive charts. It is a fantastic way to understand how agent infrastructure behaves under load, helping you build smarter, more predictable developer tools.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 clawdbrunner/openclaw-graphiti-memory

openclaw-graphiti-memory

Multi-agent AI teams can now share a unified, evolving memory without running into constant file conflicts. The openclaw-graphiti-memory project introduces a clever three-layer memory system designed specifically for OpenClaw setups. It combines private local files for individual agent tasks, read-only shared files for stable team rosters, and a dynamic, temporal knowledge graph powered by Graphiti and Neo4j. This means agents can query a central brain to recall exactly when a decision was made or what another agent discovered, all while keeping their own working notes separate. It is a practical blueprint for building collaborative, well-coordinated digital workforces.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 miaai-lab/deepseek-v4-flash-dspark-2x-dgx-spark

deepseek-v4-flash-dspark-2x-dgx-spark

deepseek-v4-flash-dspark-2x-dgx-spark is the multi-node recipe that finally lets you run DeepSeek's fast model at scale without crashing under heavy traffic. Normally, running this model with speculative decoding across multiple hardware nodes causes memory confusion and errors as soon as multiple people ask questions at the same time. This project solves that by applying a clever concurrency patch that links memory slots to specific user sessions, preventing data corruption. Now you can easily run up to sixteen fast, simultaneous conversations with zero errors. Grab the code and scale your local setups tonight.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 keijiro/audiotailor

Audio Tailor

audiotailor is the Unity editor extension that lets you clean up and loop sound assets without ever leaving your game engine. Instead of jumping back and forth to an external audio editor just to fix a messy file, you can trim dead air, boost volume, and convert files to mono right inside your inspector. The coolest part is how it handles looping. It blends the start and end of a sound together using a smooth crossfade, making it incredibly easy to build seamless ambient tracks and music loops. It is a massive time-saver for keeping your audio workflows simple.

🆔 @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
📦 plummerssoftwarellc/tinyretropad

TinyRetroPad

Build a fully functioning, Notepad-style Windows text editor that fits into an unbelievably small two-and-a-half kilobytes. That is where tinyretropad comes in. It is a size-obsessed, minimalist text editor written in x86 assembly. By stripping away every piece of unnecessary overhead and using clever compression at build time, it packs a complete set of classic menus, file dialogs, printing capabilities, search and replace, and a real-time status bar into a tiny binary. It is a masterclass in hyper-efficient programming that squeezes maximum utility out of every single byte. Grab the code, compile it yourself, and see how much punch you can pack into a microscopic file.

📰 https://news.ycombinator.com/item?id=48732565

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 feelingai-team/codebrain

CodeBrain

CodeBrain is the model context protocol plugin that finally gives your coding agents real compiler-grade diagnostics and structural code search. Instead of letting an AI agent blindly poke around your codebase and burn through expensive tokens, this tool connects right to your language servers to map your files, find symbols, and instantly validate changes. It catches type errors and broken imports before running a full build, auto-recovering when agents get stuck in loops or crash. It works out of the box with Python, TypeScript, and Go, reducing token costs by over sixty percent. Grab it today to make your coding agents genuinely smart.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 vercel-labs/knowledge-agent-template

Knowledge Agent Template

This open-source template lets you deploy AI agents that can search and understand your documentation without using any vector databases, chunking pipelines, or embedding models. Instead, the system spins up lightweight, isolated sandboxes and runs familiar command-line searches like grep, find, and cat directly across your files for instant and highly predictable results. It includes an administrative interface where you can monitor usage, sync content from sources like GitHub, and even chat with an AI admin agent that analyzes your server logs. Ultimately, it provides a clean, self-hostable foundation for building smart bots that instantly run on web chat, Discord, and GitHub.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 gommzystudio/device-activity-tracker

Device Activity Tracker

Device-activity-tracker is the proof-of-concept tool that demonstrates how easily your daily messaging habits can leak to outsiders without your knowledge. By measuring the round-trip time of silent delivery receipts on apps like WhatsApp and Signal, it detects if your device is active, in standby, or offline. When you receive a background message probe, your phone automatically sends back a quick receipt; because your processor responds faster when you are actively using the screen than when it is locked in your pocket, this tool uses those tiny millisecond differences to map your exact daily routines. It highlights a massive, unpatched privacy gap in modern secure messaging.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 nicobailon/visual-explainer

Visual Explainer

Turn dry terminal outputs and messy text diagrams into gorgeous, interactive web pages and slide decks you actually want to read. When your AI agent tries to explain a system architecture or run a code review, it usually dumps a wall of unreadable monospace text, broken tables, and ASCII art. This tool fixes that by generating self-contained HTML files complete with clean typography, responsive tables, dark mode, and zoomable flowcharts. You can even generate high-quality slide decks instantly. It is a brilliant way to visually audit plans, review code diffs, and map out projects without drowning in terminal clutter.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 gvclab/personalive

PersonaLive

Animate any portrait photo in real time using a live webcam feed to drive the facial movements, expressions, and poses. It relies on a clever diffusion framework designed specifically for live streaming, letting you broadcast infinite-length animations without running out of video memory. Instead of lagging behind, it processes your expressions instantly, keeping the generated character completely synced to your real-life speaking rhythm. It is incredibly fun because you can suddenly stream as a completely different character, historical figure, or digital avatar with natural, fluid facial movements. Grab a portrait, start up your webcam, and watch your new persona come to life instantly.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 memmachine/memmachine

MemMachine

MemMachine is the open-source memory layer that finally gives your AI agents a long-term memory with just five lines of code. Instead of letting your bots start from scratch every single time they reboot, this clever tool lets them actually learn, store, and recall information from past conversations. It organizes chat histories into structured episodic memory using a graph database, while keeping user facts tidy in SQL. If you are building AI assistants, this is the easiest way to make them feel truly personalized and context-aware. Check it out to give your agents some real staying power.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 wesammustafa/claude-code-everything-you-need-to-know

Claude Code Everything You Need to Know

This brilliant GitHub repository is a masterclass in using Claude Code, Anthropic's official terminal-based assistant that can actually read your local repository, edit files, and run tests in place. Instead of just copy-pasting code back and forth into a browser, this guide shows you how to hook Claude directly into your development workflow using custom slash commands, lifecycle hooks, and automated agent teams. It is a goldmine of practical examples, custom scripts, and specialized system prompts that help you automate repetitive chores like writing tests or reviewing pull requests. It is the ultimate playbook for turning Claude into your most productive terminal companion.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 happier-dev/happier

Happier

Happier is the cross-device companion app that keeps your AI coding sessions alive when you step away from your computer. It links your computer to your phone, web browser, or desktop app with end-to-end encryption. When you run AI assistants like Claude Code, Gemini, or Codex locally, you can instantly monitor, control, and continue those active sessions from your phone while grabbing a coffee. It securely bridges your local terminal to your mobile screen without losing context. You can pause, fork, or hand off active tasks between devices, making remote AI development simple and accessible from anywhere.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 bradagi/awesome-cli-coding-agents

Awesome CLI Coding Agents

An open-source project called claw-code racked up one hundred thousand GitHub stars faster than any repository in history after a major AI assistant's source code leaked. You can find this project and dozens of others inside awesome-cli-coding-agents, a curated directory of over ninety terminal-native AI programing tools. Instead of using clunky chat interfaces, these agents live directly in your command line, giving them direct access to your filesystem so they can run tests, edit files, and fix their own errors on the fly. It is the ultimate directory for finding the perfect autonomous terminal companion to help write your next codebase.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 joshavant/clawbox

Clawbox

You can spin up fully configured, isolated macOS virtual machines on your Apple computer with a single command using clawbox. This tool completely automates the tedious setup process, letting you build and launch virtual environments running the OpenClaw platform. It uses high-performance virtualization to run multiple machines side-by-side, synchronizing your local code bidirectionally so that any host-side changes instantly update inside the running system. It even handles system configuration, installing Homebrew, setting up SSH, and adding utilities like Playwright or Tailscale automatically. It is a fantastic way to develop and test software in clean, dedicated environments without cluttering your main operating system.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 jvdillon/netv

neTV

Stream your favorite live TV channels and on-demand videos through a beautifully simple, self-hosted web interface that runs right in your browser. While other media players try to do absolutely everything and end up feeling like bloated, sluggish monsters, netv keeps things incredibly lean and focused on doing just one thing right. The absolute coolest part has to be its optional real-time upscaling, which actually uses your graphics card to turn fuzzy old television broadcasts or standard-definition movies into crisp quality. It is basically the ultimate, lightweight way to enjoy your own television playlists without any of the usual hassle.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 kurikomi-labs/komi-store

Komi Store

You can now browse and install open-source software directly from developer releases on GitHub, Codeberg, and Forgejo using a single, unified app store. A clever tool called komi-store acts as a free, platform-aware discovery layer for your desktop or Android device. It automatically filters out empty repositories to only show projects with valid, installable binaries. You can easily find trending apps, browse full release histories, and even peek inside Android installation packages before installing them. It is a fantastic way to bypass traditional, restrictive app stores. Grab this tool to explore a massive library of independent, community-driven software with absolute ease.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 nicolepcx/ai-agents-the-definitive-guide

AI Agents The Definitive Guide

An upcoming O'Reilly book is providing a complete blueprint for moving beyond basic chatbots to building fully autonomous digital systems. The ai-agents-the-definitive-guide repository hosts the official hands-on code accompanying this guide, mapping out everything from memory storage to threat modeling. Instead of just showing simple API calls, it provides structured notebooks that walk you through complex multi-agent patterns, tool governance, and secure execution. It is a practical resource for anyone trying to understand how autonomous systems actually function under the hood. You can run all these examples directly in your browser to start building more reliable, self-directed software.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 neural-maze/realtime-phone-agents-course

Realtime Phone Agents Course

You can now build a fully functional real estate call center run entirely by realistic voice agents that handle live inbound and outbound phone calls. The realtime-phone-agents-course is a step-by-step practical guide that teaches developers how to stitch together a highly responsive voice pipeline. Instead of lagging toy demos, it shows you how to deploy open-source speech-to-text and text-to-speech models on cloud GPUs for lightning-fast conversations. The standout feature is its use of advanced vector search to let agents instantly query complex, multi-attribute databases, like matching a home buyer's exact budget and location mid-call. Check out this guide to start building production-ready voice systems.

🆔 @hackernewsgithubprojects