#typescript

AG Kit is an open-source toolkit for building and managing agent workflows in Google Antigravity. It gives you rules, skills, specialist agents, memory, workflow commands, and a built-in safety check, so you can work faster, stay organized, and reduce risky command mistakes. It is released under the MIT License, which means you can use, change, and share it with very few limits, as long as you keep the license and copyright notice.

https://github.com/vudovn/ag-kit

#typescript #data_science #duckdb #geospatial #maplibre #maplibre_gl_js #tauri_app

GeoLibre is a free, open-source GIS app for viewing, exploring, and analyzing map data, and it works in your browser, on desktop, on mobile, and in Jupyter notebooks while keeping your data local and private. It gives you an easy way to make maps, use 3D views, and work with different places, so you can handle geospatial data without installing heavy software or moving your files online.

https://github.com/opengeos/GeoLibre

#php #coding_conventions #php_codesniffer #phpcs #ruleset #wordpress_development #wordpress_standards

WordPress Coding Standards for PHP_CodeSniffer is a tool that checks WordPress PHP code for quality, style, and security issues. It works with Composer, needs PHP 7.2 or higher, and can scan code from the command line, your IDE, or automated tests. You can use it to find problems early, follow WordPress rules more easily, and keep your code cleaner and safer.

https://github.com/WordPress/WordPress-Coding-Standards

#python #ai #assistant #language_model #machine_learning #python #speech #speech_synthesis #speech_to_text #speech_translation

I can help you build a fast, modular voice agent that turns speech into text, sends it to a language model, then speaks the answer back. It works with open-source or hosted models, can run fully local on your own hardware, and supports live transcription and low-latency conversation, so you get a flexible voice app that you can customize for speed, privacy, and different devices.

https://github.com/huggingface/speech-to-speech

#python #agent_framework #ai_agents #ai_safety #compliance #governance #microsoft #owasp #policy_engine #python #security #trust #zero_trust

Agent Governance Toolkit helps you control AI agents with policy checks, identity, sandboxing, and audit logs so unsafe actions are blocked before they happen. It lets you govern tools in a few lines of code, works with many languages and agent frameworks, and gives you compliance and security checks, which helps you launch agents more safely and prove what they did.

https://github.com/microsoft/agent-governance-toolkit

#python

book-to-skill turns a technical book, document folder, or other source files into a reusable agent skill that your coding assistant can load only when needed. The benefit is faster, more accurate help with far fewer tokens, so you can ask questions from the real content instead of rereading PDFs or risking weak answers.

https://github.com/virgiliojr94/book-to-skill

#html #a_share #algorithmic_trading #backtesting #china_stock_market #kline #local_first #market_data #mcp #quant_research #quantitative_finance #stock_data #stock_market #technical_analysis #time_series_database

This is a local stock data engine that stores A-share, ETF, and tick data on your own computer, then cleans, adjusts, and organizes it for fast research and backtesting. It helps you work offline, avoid remote API limits, and quickly query data, calculate indicators, and use Python, HTTP, Excel/WPS, web pages, or AI tools from one local setup.

https://github.com/hello245m/free-stockdb

#typescript

OpenWork is a free, open-source app for sharing AI workflows across macOS, Windows, and Linux. You can use the same skills, plugins, and connected services in different AI agents, so work you set up once is easy to reuse and share. The main benefit is saving time and keeping tools consistent for you, your team, and your devices, while the admin tools help larger groups manage access and shared connections.

https://github.com/different-ai/openwork

#objective_c

This is a research demo that shows Apple Neural Engine can train small transformer models, not just run inference. It may help you learn from its benchmarks, reuse the MIT-licensed code, or adapt the ideas for your own AI hardware work, but it is not a production tool and still has major limits like low efficiency and CPU fallback.

https://github.com/maderix/ANE

#cuda

FlashKDA is a fast CUDA kernel library for Kimi Delta Attention, built with CUTLASS and made for SM90+ GPUs with CUDA 12.9+ and PyTorch 2.4+. It can plug into flash-linear-attention as a backend, and on H20 it reports about 1.72× to 2.22× faster prefill than the existing baseline. This can help you run attention faster, with less deployment work, especially if you use supported hardware and the fixed K = V = 128 setup.

https://github.com/MoonshotAI/FlashKDA

#python #deep_face_swap #deep_learning #deep_neural_networks #deepface #deepfakes #deeplearning #face_swap #faceswap #fakeapp #machine_learning #myfakeapp #neural_nets #neural_networks #openfaceswap

FaceSwap is a computer tool that uses deep learning to recognize and swap faces in photos and videos, and it works best on Windows, Linux, or Mac with a modern GPU. You first extract faces, then train a model, then convert new images or video, so you can create face swaps or learn how AI face recognition works more easily.

https://github.com/deepfakes/faceswap

#rust #ai_tools #code_review #rust #tui

This is tuicr, a terminal code review tool with vim keybindings that lets you read diffs, add comments, and send reviews to GitHub, GitLab, clipboard, or stdout. It works with git, jj, and Mercurial, so you can review changes in one place and save time when checking code or sharing feedback.

https://github.com/agavra/tuicr