Найти похожее

#python#agent#agents#ai#anthropic#claudecode#llm#llms#openai Open SWE is a free, open-source framework to build internal coding agents like those at Stripe, Ramp, and Coinbase. Trigger it via Slack, Linear, or GitHub (@openswe) to research codebases, plan tasks, code, test, review, and auto-open PRs in secure cloud sandboxes—running parallel jobs without your machine's resources. Customize models, tools, and workflows easily. You benefit by automating routine coding, slashing review cycles and production time by 30-50%, freeing you to focus on high-value work while ensuring safe, high-quality changes. https://github.com/langchain-ai/open-swe

#python#bytetrack#multi_object_tracking#oc_sort#sort Trackers is a simple Python library (pip install trackers) for multi-object tracking that plugs into any detection model like YOLO. Use it via CLI on videos/webcams or in Python code with trackers like ByteTrack (top performer on MOT17/SportsMOT benchmarks) to add labels and trajectories. Evaluate with MOT metrics too. Benefit: Quickly add reliable object tracking to your computer vision projects for real-time apps like traffic or sports analysis, saving time on custom code. https://github.com/roboflow/trackers

#python#mllm#point_clouds#scene_understanding#spatial_intelligence SpatialLM is a powerful 3D language model that turns complex 3D point cloud data from videos, RGBD images, or LiDAR into clear, structured 3D scene layouts showing walls, doors, windows, and objects with labels. It works without needing special equipment and can detect user-specified object categories. This helps you understand and analyze indoor spaces better, useful for robotics, navigation, and 3D design. You can run it on your data, visualize results, and even customize detection tasks easily, making 3D scene understanding more accessible and flexible for many applications. https://github.com/manycore-research/SpatialLM

#python#face_animation#image_animation#video_editing#video_generation LivePortrait is a tool that uses AI to animate still photos, making them look like videos. It works by identifying key facial features and adding realistic movements. This technology helps create lifelike videos that can be used for personalized communication. The benefit to users is that they can easily create engaging animated portraits from static images, which can be fun and useful for various applications like social media or storytelling. https://github.com/KwaiVGI/LivePortrait

#apacheSpark#ETL#dataEngineering#Python 🎚 Apache Spark 3 for Data Engineering and Analytics with Python [Video] 🗣David Mngadi 🌐 Inglés ⚖️2.1GB 🔗Link ----- Canal principal:@repo_science Cupones: @freecoupons_reposcience -----

#python#emulation#open_source#retrogaming#rommapp#self_hosted RomM is a powerful, self-hosted ROM manager that helps you organize, browse, and play your game collection easily through a clean web interface. It supports over 400 gaming platforms and enriches your library with metadata, artwork, and achievements from popular databases like IGDB and Retroachievements. You can play games directly in your browser using built-in emulators, manage multi-disk games, DLCs, mods, and share your collection with friends securely. RomM works on desktop and mobile, making game management simple and accessible anywhere, enhancing your gaming experience by keeping everything organized and playable in one place. https://github.com/rommapp/romm

⚡️[🇷🇺] #Ремонт/#Производња: Једноставна и практична роботска решења - процес комплетирања лаких јуришних робота-деминера на првој линији фронта#мај_2026 📝 → Специјалисти 92. инжеријског пука ГА „Запад“ представили лаког робота за даљинско разминирање, намењеног борбеној употреби у зони СВО. Његова основна намена је „безбедно отварање коридора за јуришне јединице“ кроз противничка минска поља (запречавање). ✖️ Опис средства Технички носилац функције је предњи плуг[#видео], постављен тако да изазива активирање искључиво противпешадијских мина[3]. Оне су примарно намењене дејству по живој сили, па њихово уклањање непосредно испред јуришне пешадије има директну последицу на значајну редукцију губитака у ж/с. ** Као главна инжењерска особеност истиче се релативно мала маса комплекса: она је, како се наводи, „специјално одабрана“ тако да не доводи до активирања противтенковских мина[4]. Тај детаљ указује да је систем пројектован за употребу у пешадијским, а не оклопно-механизованим јединицама. ✖️Тактичке погодности - лака израда + ефикасност ван тенкопроходних праваца Предност оваквог средства није у замени класичних инжењеријских машина, већ у попуњавању празнине између пешадијских деминерских јединица и тешких средстава за разминирање. Лаки робот може да делује тамо где је пролаз тешке технике ризичан, спор или физички ограничен. Његова практична вредност је највећа на уским правцима, у урбаним прилазима, шумским појасевима и зонама где тешка техника споро маневрише. → Линк: /t.me/borbeni_efektivi → Извор: достављени материјал 🪖#Русија〣#Украјина〣#СВО〣#Инжењерија〣#Разминирање〣#НРТК〣#Искуства〣#Копнена_војска 🇷🇸https://t.me/borbeni_efektivi

#python#3d_reconstruction#3d_vision#monocular_depth_estimation#monocular_geometry_estimation MoGe-2 is a powerful tool for estimating 3D geometry from single images. It can create detailed point maps, depth maps, and normal maps with high precision. This model is especially useful because it can predict geometry in metric scale, meaning it provides accurate measurements. It also enhances visual sharpness, making it better than previous versions. Users benefit from MoGe-2 by getting precise 3D information from just one photo, which is helpful for applications like robotics or video games. It's fast and works well with different image sizes. https://github.com/microsoft/MoGe

#python#mootdx#pytdx#tdx#tdxpy mootdx is a free, open-source Python tool that helps you easily read and use stock market data from Tongdaxin on Windows, MacOS, and Linux. It supports Python 3.8+ and can read offline daily, minute, and timeline stock data, as well as online real-time market quotes and financial files. You can install it simply with pip and use it to get detailed stock info for analysis or trading. This saves you time and effort by providing a ready-made, flexible way to access and work with Chinese stock market data in Python. It’s great for learning, research, and personal projects but not for commercial use[1][4]. https://github.com/mootdx/mootdx

#python#bot#trading#aws 🐍 DYDX Pairs Trading Bot Build in Python Running in the Cloud Develop an advanced decentralised trading bot which runs on AWS and sends private messages to your Telegram account 🔗Link ----- Main channel: @repo_science Coupons: @freecoupons_reposcience -----

11.12.2025. Северная часть квартала 13. Продолжается отсыпка и трамбовка песка. Содается насыпь. Отсыпано уже до конца вырубки, почти до строительной площадки у Акуловского водоканала. Рядом с межевым знаком 124 в насыпь вкопана труба большого диаметра. Отдельные экземпляры подлесника сохранились с северной стороны от вырубки, все что оставалось рядом со стройкой южнее, теперь окончательно засыпано, в т. ч. и у меток ФГБУ. #квартал_13#отсыпкапеском#строительнаятехника#межевойзнак#аншлаги#режимохраны#квартальныйстолбик#подлесник#краснаякнига#видео#фото#декабрь2025

#python#agent#ai_agents#memory#memoryscope#rag#reme ReMe is a memory toolkit for AI agents with file-based (Markdown files for easy editing) and vector-based systems to fix limited context and stateless chats. It auto-summarizes talks, saves key facts like preferences, and recalls them next time using hybrid search. Install via `pip install reme-ai`, set API keys, and use ReMeCli or Python code for smart agents. You benefit by building persistent, learning agents that remember your needs, work faster on repeat tasks, and feel more natural without starting over. https://github.com/agentscope-ai/ReMe