Find similar content

#python#docker#fastapi#kbqa#kgqa#llms#neo4j#rag#vue Yuxi-Know (语析) is a free, open-source platform built with LangGraph, Vue.js, FastAPI, and LightRAG to create smart agents using RAG knowledge bases and knowledge graphs. The latest v0.4.0-beta (Dec 2025) adds file uploads, multimodal image support, mind maps from files, evaluation tools, dark mode, and better graph visuals. It helps you quickly build and deploy custom AI agents for Q&A, analysis, and searches without starting from scratch, saving time and effort on development. https://github.com/xerrors/Yuxi-Know

#cplusplus#firefox#firefox_based#firefox_browser#zen_browser Zen Browser is designed to help you browse the internet with balance between speed, privacy, and productivity. It offers features like **workspaces** to organize your tabs, **compact mode** to reduce distractions, and **split views** to multitask. You can customize almost everything to fit your needs. Zen is built on Firefox, ensuring you get the latest security updates. It's available for Windows, macOS, and Linux, and is open-source, allowing community contributions. This means you can enjoy a fast, secure, and highly personalized browsing experience. https://github.com/zen-browser/desktop

#python#chatbi#deepseek#llm#nl2sql#rag#sqlbot#text_to_sql#text2sql SQLBot is an easy-to-use intelligent system that turns natural language questions into SQL queries using advanced AI models and retrieval-augmented generation (RAG). You just need to set up your AI model and data source to start asking questions about your data. It integrates smoothly with other business systems and AI platforms, making it simple to add smart data querying to your apps. It also ensures data security with workspace-based resource isolation and fine-grained access control. You can quickly deploy it on a Linux server using Docker, enabling fast, secure, and intelligent data interaction without needing deep SQL knowledge. This saves you time and improves data accessibility. https://github.com/dataease/SQLBot

#cplusplus#hap#mid_360#ros#ros2 Livox ROS Driver 2 connects your Livox LiDARs like HAP and Mid360 to ROS (Noetic) or ROS2 (Foxy/Humble/Jazzy) on matching Ubuntu versions. Clone the repo in a workspace/src folder, build Livox-SDK2, then run ./build.sh with your ROS version, and launch with roslaunch or ros2 launch files from launch_ROS1/ROS2 folders—edit JSON configs for IP, ports, frequency (up to 100Hz), and formats. This lets you quickly test and visualize point clouds in RViz for robotics development, saving time on setup and debugging. https://github.com/Livox-SDK/livox_ros_driver2

#cplusplus#compositor#cpp26#wayland#wayland_compositor Hyprland is a modern Wayland compositor that offers dynamic tiling and floating window management. It provides many customization options, powerful plugins, and beautiful visual effects like animations and shadows. Hyprland is designed for performance and efficiency, making it a great choice for users who want a customizable and visually appealing desktop environment. It allows users to easily switch between different window layouts and offers features like tearing support for better gaming performance. This makes Hyprland beneficial for users seeking a flexible and high-performance desktop experience. https://github.com/hyprwm/Hyprland

#python#ai#ai_chat#chatgpt#enterprise_search#gen_ai#information_retrieval#llm#llm_ui#nextjs#python#rag Onyx is an open-source AI platform that lets you easily create and use custom AI chat agents with any large language model (LLM). It supports advanced features like web search, document search, code execution, and connecting to over 40 apps, all while keeping your data secure and private. You can deploy it quickly on your own servers or cloud, making it great for individuals or large teams. Onyx helps you get accurate, reliable answers from your own knowledge and automates tasks, improving productivity and collaboration in your work. It’s flexible, secure, and free to start with. https://github.com/onyx-dot-app/onyx

#MLEngineer#DataScientist#remote#parttime#project#NLP#RAG#finetuning#USA#удаленно#парттайм#AI#agent#LLM #Senior#Middle ML Engineer / Data Scientist / NLP Engineer 📍Удалённо, парт-тайм Занятость: проектная почасовая Оплата: 2000 - 2500₽ /час (USD ≤30) AInnovator — занимается разработкой и внедрением AI/ML решений для среднего и крупного бизнеса в России, США и Канаде Задачи: ▫️Написание RAG-пайплайнов ▫️Обучение LLM на корпоративных датасетах заказчиков on-premise ▫️Построение моделей кластеризации и семантического поиска ▫️Создание мультиагентных LLM-систем ▫️Интеграция с бэкендом (FastAPI, Flask) ▫️Работа с реляционными БД (PostgreSQL, alembic) ▫️Рефакторинг существующего ML-кода Формат работы: ▪️Участие в проектной команде (backend + devops) ▪️Scrumban: трек задач в Kanban + 1-2х-недельные спринты ▪️Оплата результата по фактически отработанным часам ▪️Отсутствие жесткой привязки по времени Мы предлагаем: ▫️Интересные AI-проекты на Российском и Американском рынке ▫️Возможности для творческой реализации и развития навыков ▫️Карьерный рост до Team/Tech Lead ▫️Возможность принять участие в выводе продуктов и сервисов на международный рынок ▫️Отсутствие привязки к месту и возможность оплаты труда в любую точку мира ▫️Возможность дальнейшего фулл-тайм трудоустройства (в США, РФ, Грузии) Мы предоставляем корпоративный доступ к: ▪️Cursor / WindSurf / Manus или др. ▪️Promptmetheus (для удобства промпт-инжиниринга) ▪️Надежному VPN-сервису Наши приоритеты (которые ожидаем и от вас): ▫️Быстрая и прямая коммуникация ▫️Ответственность за выполнение взятых обязательств ▫️Соблюдение сроков без напоминаний 💭 Связаться: @hr_aisors — отправляйте CV, пригласим на скрининг и обсудим детали

#python#agents#document_search#evaluation#guardrails#llms#optimization#prompts#rag#vector_stores Ragbits is a tool that helps build and deploy GenAI applications quickly. It offers features like swapping between many language models, ensuring safe interactions with these models, and connecting to various data storage systems. Ragbits also includes tools for managing data and testing prompts, making it easier to develop reliable AI applications. This helps users create more accurate and efficient AI systems by integrating the latest data and reducing errors. Overall, Ragbits makes it faster and more efficient to develop and deploy AI applications. https://github.com/deepsense-ai/ragbits

#cplusplus#android_auto#android_automotive#headunit#wireless_android_auto You can turn your car’s wired Android Auto into wireless using a Raspberry Pi and a special software called Wireless Android Auto Dongle. This DIY adapter connects your phone to the car wirelessly via Bluetooth and Wi-Fi, without needing extra apps on your phone. It works with several Raspberry Pi models and boots up quickly, connecting in under 30 seconds. After the first setup, it automatically connects every time you start your car, making your Android Auto experience seamless and cable-free. This saves you from plugging in your phone every time and keeps your car’s infotainment system working smoothly[1][2][3]. https://github.com/nisargjhaveri/WirelessAndroidAutoDongle

#python#ai_agents#ai_tutor#clawdbot#cli_tool#deepresearch#interactive_learning#large_language_models#multi_agent_systems#rag DeepTutor v1.0.0 is an open-source AI tutoring tool with personalized TutorBots, unified chat modes for solving problems, quizzes, research, and math animations, plus knowledge bases from your PDFs, persistent memory of your learning style, AI co-writing, and guided plans—all via easy web, Docker, or CLI setup. You benefit by getting a smart, evolving study companion that adapts to you, boosts understanding with interactive tools, and saves time on tough topics without starting over. https://github.com/HKUDS/DeepTutor

#вакансия#mlops#engineer#llm#vllm#hugginface#rag#embeddings#k8s#docker#deckhouse#Langfuse#LlamaIndex#remote Вакансия: MLOps-инженер Компания: АО СимбирСофт Формат работы: удалёнка Занятость: полная занятость Ищем MLOps инженера в РФ 👨‍💻 🚀 Нам нужен инженер, готовый развивать инфраструктуру LLM-платформы. Твоими задачами станут поддержка и развитие сервисов для больших языковых моделей, интеграция инструментов, настройка мониторингов и обеспечение безопасности данных. 🔍 Опыт работы с: - Большими языковыми моделями (vLLM, TGI, Hugging Face) - Python (FastAPI, скрипты, CLI) - Архитектурой RAG и embedding-моделями - Prometheus/Grafana - Система аутентификации (Keycloak, JWT) - Kubernetes, Docker, CI/CD 💡 Будут полезны знания: - Deckhouse или других дистрибутивов Kubernetes - Langfuse, LlamaIndex, PostgreSQL Vector, Chroma - Принципов MLOps и интеграции сторонних API ✅Условия: - Удаленный формат работы. - Гибкое начало рабочего дня. - Широкий технологический стек, сотни проектов. Можно разрабатывать IT-решения для разных отраслей, пробовать новые технологии. - Помогаем прокачаться во всех интересующих направлениях: стать тимлидом, архитектором, разработчиком. - Имеем развитую систему наставничества, проходим сертификацию за счет компании, участвуем в конференциях. Активно обмениваемся опытом, проводим внутренние и внешние митапы, прокачиваем hard и soft skills. Присоединяйся к нам!✨ Если заинтересовала вакансия, буду рада обсудить в тг: https://t.me/gulnara_s28 ʕ ᵔᴥᵔ ʔ

#typescript#12_factor#12_factor_agents#agents#ai#context_window#framework#llms#memory#orchestration#prompt_engineering#rag The 12-Factor Agents are a set of proven principles to build reliable, scalable, and maintainable AI applications powered by large language models (LLMs). They help you combine the creativity of AI with the stability of traditional software by managing prompts, context, tool calls, error handling, and human collaboration effectively. Instead of relying solely on complex frameworks, you can apply these modular concepts to improve your existing products quickly and reach high-quality AI performance for real users. This approach makes AI software easier to develop, debug, and scale, ensuring it works well in production environments[1][3][5]. https://github.com/humanlayer/12-factor-agents