56 subscribers
7.24K videos
7.85K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
📦 horizonrobotics/uni3r

Uni3R: The New Way to Reconstruct 3D Scenes

Uni3R completely changes 3D scene perception by generating full 3D reconstructions from unposed multi-view images in a single forward pass. This framework uses a Cross-View Transformer to fuse information from arbitrary input views, regressing a dense set of 3D Gaussian primitives that contain both geometry and open-vocabulary semantic data. By eliminating the need for time-consuming per-scene optimization, it enables high-fidelity novel view synthesis, 3D semantic segmentation, and accurate depth prediction simultaneously. This breakthrough simplifies how we interpret 3D environments, providing a fast and powerful tool that moves us toward more generalizable and unified 3D scene understanding.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 cursed-me/loopers-oss

Stop AI Bill Shock with Loopers

Loopers is the infrastructure firewall that keeps your AI spending in check by preventing unexpected budget overruns. This high-performance tool acts as a transparent reverse proxy between your application and over five hundred AI models. It uses atomic Redis transactions to enforce strict budgets and includes a dedicated circuit breaker to stop runaway agent loops before they drain your resources. With its zero-storage architecture, it keeps your API keys secure while adding only sub-millisecond latency. Deploy this firewall to ensure your autonomous agents stay within limits, protecting your wallet from costly and accidental usage spikes.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 github30/reproducible-photorealistic-nano-banana-pro-json-prompts

Master Photorealistic AI Images with Nano Banana JSON Prompts

The repository is a collection of structured JSON templates that enables high-fidelity photorealistic image generation for Nano Banana Pro. By replacing standard natural language prompts with organized data structures, it solves the problem of concept bleeding and inconsistent details in AI art. Users can surgically define specific attributes like lighting, camera settings, and subject characteristics to ensure repeatable, professional results across different generations. This approach allows for precise control over complex scenes, making it an essential resource for creators seeking consistent character identity and high-quality photography styles without the ambiguity often found in traditional prompt writing.

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

Build and Debug Shell Pipelines Faster with Rura

Rura is an interactive terminal scratchpad that replaces the tedious cycle of editing, running, and adjusting complex shell pipelines. It provides a live visual workspace where you can build commands like grep or sort and see the output update in real time as you type. You can inspect intermediate stages of a pipe, perform line-based diffs between outputs, and save frequently used command sequences as presets for quick access. With customizable themes, regex search, and support for multiple shells, this tool simplifies the process of refining data pipelines. Use it to prototype complex logic efficiently without leaving your terminal.

📰 https://news.ycombinator.com/item?id=48681858

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 asimons81/hermes-gpt

Control Hermes Agent with MCP Using Hermes GPT

Integrate your local Hermes Agent with Model Context Protocol clients by using this standalone sidecar tool. It imports internal agent functionality at runtime, allowing you to safely expose features like file management, memory access, and cron scheduling without modifying the original source code. The project features a tiered operator mode that enforces read-only defaults, dry-run previews, and explicit authentication requirements to keep your system secure. With built-in diagnostic and recovery tools, it provides a reliable way to bridge your agent tasks into modern AI interfaces while maintaining strict control over what changes occur on your machine.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 mandiclab/djc-diy

Build Your Own DJ Controller from Scratch

Construct your own personalized DJ controller at home using open-source hardware and software. This project provides everything you need to build a custom MIDI device, including 3D printable case files, a detailed parts list featuring an Arduino Pro Micro, and firmware to get you started. By following the assembly guide, you can solder electronic components like buttons, faders, and rotary encoders to create a fully functional unit. Once complete, it connects seamlessly with Mixxx DJ software for immediate use. Dive into the world of custom hardware and start mixing tracks on your very own handmade controller today.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 sgl-project/genai-bench

Benchmark LLM Serving Performance with GenAI Bench

GenAI Bench provides a unified framework for measuring the token-level performance of large language model serving systems. This tool simplifies the benchmarking process by offering a command-line interface to initiate performance tests against various backends, paired with a live dashboard for real-time monitoring of metrics like throughput and latency. Beyond live tracking, the experiment analyzer generates detailed Excel reports and visual plots to compare performance across different traffic scenarios and concurrency levels. It supports multiple task types, including text generation and embedding requests, giving developers clear insights into how their model serving infrastructure behaves under load.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 suvojeet-sengupta/suvmusic

Exploring SuvMusic: An Advanced Android Audio Player

SuvMusic is a feature-rich Android application designed to provide a comprehensive and highly customizable music streaming experience. Built with native C++ audio components, the project integrates advanced features like spatial audio, a pitch shifter, and a limiter to enhance playback quality. It supports complex functionalities such as synchronized lyrics, Last.fm scrobbling, and a shared listening mode for social music consumption. With a modern interface, extensive UI customization options, and built-in recommendation engines, the software transforms how users interact with their audio libraries. Dive into this codebase to see how it bridges professional-grade audio processing with an intuitive mobile environment.

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

Build READMEs Faster with Markdrop

Markdrop is the visual editor that finally makes creating polished documentation and README files effortless through an intuitive drag-and-drop interface. This web-based tool simplifies markdown generation by providing real-time previews and a versatile block-based builder for everything from tables and diagrams to code snippets and badges. With built-in support for cloud synchronization, offline work, and secure user accounts, it ensures your content stays backed up across all devices. Whether you are crafting technical guides or personal profiles, its flexible design allows you to export your work cleanly. Start turning your ideas into beautiful markdown content today.

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

Peerd: The Browser-Native AI Agent Harness

Peerd is the browser-native AI agent harness that finally brings autonomous task execution directly into your existing web sessions. As a Chrome and Firefox extension, it runs a full agent loop inside your browser, allowing you to drive active tabs, execute shell commands in sandboxed WebAssembly Linux virtual machines, and manage client-side JavaScript notebooks. By utilizing your own provider keys and browser-level security, it operates without backends or telemetry. It even enables peer-to-peer sharing of agent-built applications using WebRTC. This experimental tool turns your browser into a powerful, privacy-focused engine for automated workflows and decentralized collaboration.

📰 https://news.ycombinator.com/item?id=48646165

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

Roomify: AI-Powered Architectural Rendering

Roomify is the architectural visualization platform that turns flat floor plans into photorealistic 3D renders with ease. Built with React and the Puter cloud platform, it leverages advanced AI models like Claude and Gemini to process your designs. You can generate stunning 3D imagery, compare your original sketches against the final result, and manage your projects with persistent metadata and high-performance storage. The system also includes a global community feed to showcase your architectural creations. Dive into this project to master serverless workflows and AI-driven visualization for your next design task or creative digital portfolio project.

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

Astryx: An Agent-Ready Design System

Astryx is an open-source design system that enables both developers and AI agents to build consistent, accessible interfaces using the same shared tooling. Born from years of internal development at Meta, it provides a library of over ninety React-based components that support features like automatic spacing compensation and flexible, themeable CSS variables. Its architecture is specifically designed to be agent-ready, offering JSDoc annotations and a command-line interface that allows AI assistants to scaffold, browse, and document components effectively. By offering transparent, composable primitives, this system helps teams streamline development and maintain high-quality UI standards across diverse application environments.

📰 https://news.ycombinator.com/item?id=48682464

🆔 @hackernewsgithubprojects
😍😍😍🙏🙏🙏🫶🫶
This media is not supported in your browser
VIEW IN TELEGRAM
📦 modelplaneai/modelplane

Orchestrate AI Models Anywhere with Modelplane

Modelplane is the open source control plane that finally simplifies managing AI model infrastructure across any cloud or local environment. Built on Crossplane, it functions as an active reconciliation engine that lets you declaratively define and orchestrate your entire inference stack. It handles complex tasks like provisioning inference clusters, scheduling models, scaling replicas, and caching weights across multi-node setups without locking you into a single provider. Whether you are running a single GPU or massive distributed deployments, Modelplane gives you the tools to consistently automate your infrastructure, ensuring your AI systems remain reliable and scalable regardless of where they run.

📰 https://news.ycombinator.com/item?id=48646721

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 vasuki-re/istanpdf

IStanPdf: The Offline PDF and DOCX Utility

IStanPdf is the Android utility that handles all your document tasks without needing an internet connection. It serves as a completely offline alternative to online conversion services, letting you merge, split, reorder, or remove pages from PDFs and DOCX files directly on your phone. By bundling LibreOffice binaries to power its core operations, the app keeps your files secure and local while eliminating paywalls and upload limits. It is a practical tool for anyone who wants to manage their documents efficiently on the go. Try it out to take full control of your document editing workflow today.

🆔 @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
📦 jinyangwu/opid

OPID: On-Policy Skill Distillation for Agentic RL

Enhance agentic reinforcement learning performance by transforming completed episode trajectories into hierarchical hindsight skills. OPID functions as an on-policy skill distillation framework that routes both episode-level and step-level skills during training. By providing dense token-level supervision, it eliminates the need for external skill retrievers or privileged context during inference. This approach proves effective across complex environments like ALFWorld, search-based QA, and WebShop, consistently outperforming outcome-only reinforcement learning and standard skill-distillation baselines. Adopting this framework allows developers to build more efficient, context-aware agents that leverage hindsight to guide decision-making effectively throughout their training process.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 opendatabox/awesome-agent-memory

Master AI Agent Memory Systems

Navigate the complex landscape of AI agent memory by using this curated taxonomy that organizes various systems across four distinct axes. This resource helps developers and researchers understand the evolution from simple sequential context to advanced topological structures and multi-paradigm hybrid containers. It provides a structured overview of essential reference baselines and critical benchmarks used to evaluate memory performance, retrieval fidelity, and operational stability. Whether you are building long-term memory for intelligent agents or studying the latest academic surveys, this repository offers a centralized foundation to master how agents remember, store, and utilize information effectively.

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

Automate Windows Tweaks with OptimizerNXT

Automate complex Windows configurations using a powerful command-line interface designed for system administrators and power users. This tool streamlines system management by executing YAML-driven scripts to handle registry keys, DNS settings, startup programs, and service controls efficiently. It enhances privacy and performance by allowing you to batch uninstall unwanted applications and disable telemetry or unnecessary background services safely. For added security, the system enforces cryptographic signatures on all configuration files to ensure only verified operations run on your machine. Leverage this robust utility to gain full control over your Windows environment and optimize your daily workflow.

🆔 @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
📦 ika-rwth-aachen/ros2-depth-anything-v3-trt

Real-Time Metric Depth Estimation with ROS 2 and Depth Anything V3

This ROS 2 node achieves fifty frames per second performance by leveraging TensorRT acceleration for the Depth Anything V3 model. It transforms standard camera streams into dense metric depth maps and generates real-time three-dimensional point clouds. By subscribing to camera image and calibration topics, the system performs specialized post-processing, including focal length scaling and sky classification, to produce accurate depth data for robotics applications. Users can configure precision settings and debug visualizations through parameter files, making it a robust tool for developers working on automated driving or perception tasks. This implementation bridges advanced computer vision with high-performance robotics infrastructure.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 haxl0p4/l0p4map

Advanced Network Mapping with L0p4Map

Visualize your network infrastructure with precision using this professional-grade monitoring tool. It combines high-speed ARP discovery and robust nmap integration into a modern interactive dashboard built with PyQt6. You can automatically fingerprint devices, map hierarchical network topologies, and analyze live traffic patterns with ease. The software excels at identifying host roles and detecting potential vulnerabilities, providing security researchers with deep actionable insights into their local environments. By automating complex scanning tasks and displaying them through intuitive graph layouts, this tool transforms raw network data into a clear and manageable map. Gain full visibility into your security posture today.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 benchflow-ai/awesome-evals

Stop Guessing: A Non-BS Guide to Evaluating AI Agents

Build better AI agents by moving past basic accuracy metrics with a curated, practitioner-focused library of evaluation resources. This repository provides a high-signal, non-BS collection of papers, tools, and benchmarks, specifically designed to help developers bridge the gap between demo prototypes and production-ready reliability. You get access to a practical playbook featuring real, runnable code patterns for techniques like human-aligned LLM-as-judge scoring, pass-at-k estimation, and robust error analysis. By focusing on concrete workflows and verified, annotated resources rather than generic listicles, this project helps you ship software with confidence and gain clarity on how your agents actually perform.

📰 https://news.ycombinator.com/item?id=48683312

🆔 @hackernewsgithubprojects