#python #ann #avx512 #embedding #embeddings #faiss #nearest_neighbor #neon #python #quant #quantization #rag #rust #simd #turboquant #vector_search

turbovec is a fast, local vector search tool that stores large embedding sets in much less memory, can search faster than FAISS in many cases, and works with Python and Rust. It helps you build private RAG systems because data stays on your machine, while online adding, filtering, and stable IDs make it easier to grow, control, and update your index without retraining or rebuilding.

https://github.com/RyanCodrai/turbovec

#python #ai #apple_silicon #benchmarks #cli #command_line_tool #gguf #gpu #huggingface #inference #llm #local_llm #ollama #python #vram

whichllm helps you find the best local AI model that fits your computer, not just the biggest one that fits. It checks your GPU, CPU, and RAM, ranks models using real benchmark data, and can also simulate other hardware, plan upgrades, and start a chat with a model in one command. This saves you time and helps you pick a model that should run well and work better for your needs.

https://github.com/Andyyyy64/whichllm

#python #google #googlecloud #skills

This repository gives you ready-made Google Cloud skills you can install with `npx skills add google/skills`, including tools for Gemini, BigQuery, Cloud Run, Firebase, GKE, and Google Cloud best practices. It helps you learn and use Google products faster, with setup help, support, and open-source licensing so you can copy, change, and share the skills freely.

https://github.com/google/skills

#python #bert #deepseek #healthcare #ios #llm #mlx #ner #on_device #on_premise #pii #pii_detection #qwen #sovereign_ai #swift #swift_package #swiftui

OpenMed is a local-first healthcare AI that runs on your own device or server, so patient data never leaves your network. It can extract medical entities, remove personal info, and use 1,000+ medical models in Python, Swift, or REST, which helps you work faster while keeping data private and avoiding cloud costs and vendor lock-in.

https://github.com/maziyarpanahi/openmed

#python #csi #diy #esp_32 #espectre #home_assistant #motion_detection #wifi #wifi_sensing

ESPectre is a cheap motion sensor that uses Wi‑Fi signal changes on an ESP32, so you do not need cameras, microphones, or wearables, and it works with Home Assistant through ESPHome.[user text] Set it up in about 10–15 minutes with basic YAML, use your normal 2.4 GHz router, and place the sensor about 3–8 meters away for best results.[user text] This helps you add private, low-cost motion detection for security, lights, energy saving, or room monitoring.[user text]

https://github.com/francescopace/espectre

#python

SkillSpector scans AI agent skills before you install them and flags risky code, hidden instructions, data leaks, and other security problems, using fast checks and optional AI review. It can scan folders, files, Git repos, and zip files, and it gives an easy risk score plus clear advice so you can decide whether a skill is safe to use.

https://github.com/NVIDIA/SkillSpector

#python

SIA is a tool that helps an AI system improve itself by using three parts: a meta-agent that sets up the task, a target agent that tries the task, and a feedback agent that studies the results and makes the next version better. This can help you test AI on your own tasks, track progress across generations, and see what changes improve performance.

https://github.com/hexo-ai/sia

#python

Music Assistant is a free, open-source tool that manages your music library by connecting to streaming services and speakers. It runs best on an always-on device like a Raspberry Pi and works seamlessly with Home Assistant for smart automation. The benefit to you is effortless control over all your music sources in one place, plus the ability to create automated routines (like playing music when you arrive home) without needing complex coding skills.

https://github.com/music-assistant/server

#python #hacktoberfest #python #test #testing #unit_testing

pytest is a free, open-source Python testing tool that helps you write small tests quickly and also handle bigger, more complex test suites. It gives clear failure messages, finds test files and functions automatically, and supports fixtures, `unittest`, and many plugins, which helps you catch bugs faster and write tests with less effort.

https://github.com/pytest-dev/pytest

#python

This is an open-source PaaS platform for building, deploying, and managing SaaS apps with tools like a developer center, API gateway, login, and desktop. It uses modern web and cloud features, supports MySQL, RabbitMQ, object storage, Docker-style deployment, Python, and Node.js, and includes a stable release note and an MIT license. It helps you create apps faster, with lower cost and less operations work.

https://github.com/TencentBlueKing/blueking-paas

#python #hacktoberfest #home_assistant #home_assistant_component #integration #tesla

This Tesla Home Assistant add-on lets you see car status and control features like climate, locks, charging, horn, lights, and location from one place. It can also manage Powerwall and solar energy data, and it may need a token and a proxy setup for newer Tesla cars; the main benefit is easier daily control and monitoring of your Tesla in Home Assistant, though frequent polling can wake the car and use more battery.

https://github.com/alandtse/tesla