AI Agents & Automation

T-MAC is an open-source AI Frameworks & Infra tool specifically designed for efficient low-bit Large Language Model (LLM) inference on CPU/NPU architectures. It utilizes a lookup table approach to accelerate the execution of LLMs, making it suitable for deployment on resource-constrained devices. The tool supports models like BitNet and offers a significant advantage over traditional dequantization-based methods by providing faster inference speeds. T-MAC aims to optimize the performance of AI models in environments where computational resources are limited, making advanced AI capabilities more accessible and practical for a wider range of applications.

SaneBox is an AI email management service designed to significantly reduce the time users spend on email, claiming savings of 3-4 hours per week. It employs sophisticated algorithms and machine learning to automatically sort incoming emails into different folders based on importance. Key features include filtering unimportant emails, one-click unsubscribing from unwanted senders via BlackHole, and a Daily Digest for a summary of less important messages. SaneBox also offers a personal follow-up assistant to ensure nothing slips through the cracks and a 'Snooze' feature to temporarily remove emails until needed. It works with every email client and service, including Gmail, Microsoft 365, and Apple iCloud, without requiring downloads or manual setup. The service emphasizes security and privacy, never selling or sharing user information and only analyzing email headers, not content or attachments.

Buyutech is a full-stack perception company specializing in camera-based sensing technologies for automotive, defense, and industrial mobility. They develop complete technology stacks, from photon to real-time perception, enabling safe and intelligent movement for vehicles, robots, and autonomous systems in various environments. Their offerings include core automotive products like analog and digital rear-view cameras, digital side mirror systems, occupant and driver monitoring systems, and surround-view camera systems. For defense and aerospace, they provide mission-critical terminal solutions, perception for aerial platforms, and situational awareness systems. Industrial mobility solutions include stereo depth cameras, 360° perception systems, AI-driven navigation modules, and blind-spot detection cameras. Buyutech integrates hardware, imaging pipelines, edge AI, fusion, and high-volume camera production to deliver highly reliable perception.

AI Doctor Persly is a mobile application designed to provide users with a personalized AI physician. By integrating with individual hospital records, the tool offers tailored health advice and answers to medical queries that arise during treatment. It aims to deliver accurate information sourced from leading medical institutions, helping users understand their conditions and treatment options more effectively. The application focuses on making complex medical information accessible and personalized, ensuring users receive relevant and trustworthy insights directly related to their health history.

Osaurus is an AI edge infrastructure solution specifically designed for macOS, allowing users to run both local and cloud-based AI models efficiently. This tool provides a native, always-on runtime environment, which is crucial for powering continuous AI workflows. It also facilitates the sharing of AI tools across various applications, enhancing productivity and integration within the Apple ecosystem. The project has recently moved to a new repository at osaurus-ai/osaurus, where all active development, issues, and releases are now managed. Users are encouraged to update their git remote to the new location to access the latest features and contributions.

Agent-S is an open-source framework designed to enable autonomous interaction with computers through an Agent-Computer Interface. Its mission is to build intelligent GUI agents capable of learning from past experiences and performing complex tasks autonomously. The framework has seen significant advancements, with Agent S3 being the first to surpass human-level performance on OSWorld. It supports various models and providers, including Azure OpenAI, Anthropic, Gemini, Open Router, and vLLM inference, and can be configured with grounding models like UI-TARS-1.5-7B. Agent-S offers a local coding environment for tasks requiring code execution, such as data processing and system automation, providing flexibility for technical users.

Brevitas is an open-source PyTorch library designed for neural network quantization, offering support for both post-training quantization (PTQ) and quantization-aware training (QAT). This tool enables developers and researchers to optimize and compress neural networks, making them more efficient for deployment on various hardware platforms. It provides quantized implementations of common PyTorch layers, such as QuantConv1d, QuantConv2d, and QuantLSTM, allowing individual tuning of quantization settings for different tensors. Brevitas is a research project from Xilinx, providing examples for ImageNet classification models to demonstrate PTQ under various configurations.

DiscordPal is an AI companion designed for the Discord platform, offering personalized interactions to enrich the digital social experience. It provides users with the unique experience of an AI lover, tailored to individual preferences. The tool focuses on creating more engaging and intimate conversations directly within Discord, making social interactions more exciting and personalized. While the website currently redirects, the core offering revolves around enhancing user engagement through AI-driven companionship, aiming to provide a distinct and tailored conversational experience.

Warp is an agentic development environment designed to modernize the terminal experience for developers. It addresses the limitations of traditional terminals and the scalability challenges of agentic development tools. Warp integrates modern UI and code editing features, allowing users to leverage its built-in agent, Oz, or run other CLI coding agents like Claude Code, Codex, or Gemini CLI. Oz functions as an orchestration platform for cloud agents, enabling the spin-up of unlimited parallel coding agents that are programmable, auditable, and fully steerable. This facilitates the automation of repetitive tasks and the parallel execution of agents in the cloud. The project is actively developed, with weekly updates and plans to open-source its Rust UI framework and parts of its client codebase.

Whisper is a general-purpose speech recognition model developed by OpenAI, trained on an extensive and diverse audio dataset. It functions as a multitasking model capable of multilingual speech recognition, speech translation, spoken language identification, and voice activity detection. The tool uses a Transformer sequence-to-sequence model, processing various speech tasks as a sequence of tokens. This allows a single model to handle multiple stages of a traditional speech-processing pipeline. Whisper offers several model sizes, including English-only and multilingual versions, with varying speed and accuracy tradeoffs. It supports command-line and Python usage, making it versatile for developers and researchers.

AI Hub is a comprehensive platform offering access to over 50 open-source and 20 proprietary AI models from leading providers like OpenAI, Deepseek, Anthropic, Qwen, and more. Users can engage in advanced AI chat, perform web searches with AI-powered insights, and utilize agent programming capabilities. The platform also supports image and voice generation. Available on iOS, Android, and the web, AI Hub aims to be a gateway for exploring multi-model AI capabilities, providing fast responses and keeping users updated on the artificial intelligence industry.

pyttsx3 is a text-to-speech (TTS) conversion library specifically designed for Python, offering the unique advantage of offline operation. Unlike many other TTS solutions that require an internet connection, pyttsx3 enables developers to integrate speech synthesis directly into their Python applications, making it ideal for environments with limited or no connectivity. The library supports a variety of voices and languages, providing flexibility for different project requirements. Its offline capability makes it a robust choice for applications where real-time, independent speech generation is crucial, such as embedded systems, local desktop applications, or projects requiring enhanced privacy.

The Stock Analysis Tool is an open-source project built using the CrewAI framework, designed to automate the process of analyzing stocks and providing investment recommendations. It orchestrates autonomous AI agents to collaborate and execute complex financial tasks efficiently. Users can input a company name, and the tool will generate a detailed report by leveraging various tools like browser scraping, internet search, calculator functions, and SEC filings (10-Q, 10-K). The tool supports both GPT-4 (default) and GPT-3.5, and also allows integration with local models like Ollama for enhanced flexibility, privacy, and customization. This makes it a versatile solution for financial analysis.

Pytorch-bert-crf-ner offers a PyTorch implementation for Korean Named Entity Recognition (NER) tagging, leveraging the power of BERT and CRF models. This open-source tool is specifically designed to assist in Korean Natural Language Processing (NLP) tasks and research. It provides functionalities to identify and classify named entities such as persons, locations, organizations, dates, and more within Korean text. The repository includes examples, data utilities, and training scripts, making it suitable for developers and researchers working with Korean language data who need to implement or experiment with NER models.

Pytorch-maddpg offers a PyTorch implementation of the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, a key approach in multi-agent reinforcement learning. This open-source project is hosted on GitHub and is designed for researchers and developers working on complex multi-agent systems. The implementation includes a modified Waterworld environment, where agents (evaders, pursuers, poisons) interact under specific physical rules, allowing for experimentation with cooperative behaviors. It supports features like agents bouncing off walls and requiring exact cooperation for rewards, making it a valuable tool for studying multi-agent coordination and policy learning.

PhishGuard Scaffold offers a unified framework for detecting and controlling phishing attacks on social media platforms. Leveraging LLaMA-based modeling, it provides deep semantic understanding and adversarial robustness to identify phishing attempts. The tool also incorporates advanced graph-based intervention strategies to control the propagation of detected phishing content. Key features include LLaMA-2-7B integration, multi-layer semantic projection, LoRA/PEFT support for efficient fine-tuning, and robust preprocessing. It also focuses on adversarial robustness through semantic perturbations and KL divergence training. For propagation control, it builds automated social networks, simulates diffusion with an Independent Cascade Model, and offers targeted intervention using greedy optimization and influence-aware selection. The framework is designed for production readiness with mixed precision training, gradient checkpointing, and comprehensive MLOps integration via MLflow and Ray Tune.

Dataherald is an open-source natural language-to-SQL engine designed for enterprise-level question answering over relational data. It enables users to set up an API from their database, allowing them to answer questions in plain English without needing to write SQL. This tool is ideal for business users who need to gain insights from data warehouses without relying on data analysts, for integrating Q+A capabilities from production databases into SaaS applications, and for creating ChatGPT plugins from proprietary data. The platform includes an engine for core NL-to-SQL functionality, an enterprise layer for authentication and business logic, an admin console for GUI-based configuration, and a Slackbot for interactive querying.

AI and RPA | UiPath combines the power of AI and Robotic Process Automation (RPA) to revolutionize business operations. The platform provides a cognitive upgrade for RPA robots, enabling them to handle a wider range of decision-making and problem-solving tasks. It helps businesses solve the 'last mile' challenge of AI deployment, accelerating AI into production. Key features include agentic automation, intelligent document processing, and process orchestration. The platform is designed to streamline workflows, increase efficiency, and boost productivity by automating complex processes and improving accuracy. It applies AI across various stages like process discovery, automation execution, and operational optimization, making it suitable for diverse industry applications such as invoice processing, claims processing, and email management.

Kedro is an open-source Python framework designed for building production-ready data engineering and data science pipelines. It emphasizes software engineering best practices to ensure pipelines are reproducible, maintainable, and modular. Key features include a project template based on Cookiecutter Data Science, a Data Catalog for connecting to various data sources and versioning, and pipeline abstraction for automatic dependency resolution and visualization with Kedro-Viz. Kedro also supports coding standards like test-driven development with pytest and flexible deployment strategies, including integration with Argo, Prefect, Kubeflow, AWS Batch, and Databricks. It aims to address the shortcomings of one-off scripts and Jupyter notebooks by promoting team collaboration and efficiency through modular, reusable analytics code.

pyannote-audio is an open-source Python toolkit designed for speaker diarization, a process that identifies 'who spoke when' in an audio recording. Built on the PyTorch machine learning framework, it offers robust capabilities for speech activity detection, speaker change detection, and speaker embedding. The toolkit includes pretrained models and pipelines, allowing users to quickly implement and experiment with audio analysis tasks. Furthermore, it supports fine-tuning of these models, enabling users to optimize performance on their specific custom datasets. This makes pyannote-audio a versatile tool for researchers and developers working with audio data.

Harmony Weekly Planner is an iOS application designed to help individuals achieve work-life harmony by focusing on mission-driven planning. Users can define a personal mission statement through a guided process and then plan their weeks around various life roles such as 'Husband,' 'Father,' or 'Professional.' The app encourages setting 1-2 meaningful goals for each role weekly, ensuring all important areas of life receive attention. Key features include native iOS alarm notifications to make important tasks urgent, Home Screen widgets for mission statements and weekly goals, and local-first data storage for privacy. Harmony aims to simplify planning and help users prioritize what truly matters, moving beyond traditional to-do lists.

AgentBench is a comprehensive benchmark designed to evaluate Large Language Models (LLMs) as agents across a diverse spectrum of environments. It encompasses 8 distinct environments, including 5 newly created domains like Operating System (OS), Database (DB), Knowledge Graph (KG), Digital Card Game (DCG), and Lateral Thinking Puzzles (LTP), alongside 3 recompiled from published datasets (House-Holding, Web Shopping, Web Browsing). The platform offers both Dev and Test splits for each dataset, requiring LLMs to generate responses thousands of times for thorough evaluation. AgentBench also introduces VisualAgentBench for evaluating and training visual foundation agents based on large multimodal models (LMMs), covering embodied, GUI, and visual design environments. It supports quick setup using Docker Compose and provides benchmarking results via a leaderboard.

Capably is an enterprise AI technology platform designed to unlock operational efficiency through intelligent automation solutions. It empowers organizations to multiply employee efficiency by automating bulk work and powering critical tasks with agentic AI. The platform offers a proprietary stack combining power, governance, safety, and adaptability, featuring an AI Platform for work automation, an APA Engine for process automation, an NLMP Interface for easy automation, and an AI Capability Library with ready-to-go, industry-specific AI capabilities. Capably provides a full partnership, from discovery to daily operations, taking ownership to deliver measurable results and deploying in weeks to prove value quickly. It supports various industries including Media & Advertising, Retail, FMCG, Healthcare, Real Estate, and Finance.

Magicflow is an AI-powered productivity coach designed to help founders and makers achieve deep work. It measures productivity, tracks deep work sessions, and identifies context-switches and distractions. The tool provides actionable insights on what fosters productive flow and what breaks it, helping users become more productive. Key features include live flow timers for focus sessions, Pomodoro timers, distraction warnings, and a glowing flow meter. It offers automatic time tracking, real-time productivity metrics, and recommended focus actions, making it a comprehensive solution for enhancing focus and optimizing work habits.