AI Agents & Automation

Agentic Radar is a security scanner designed to analyze and assess agentic systems for security and operational insights. It helps developers, researchers, and security professionals understand how agentic systems function and identify potential vulnerabilities. The tool generates a comprehensive HTML security report that includes workflow visualization, tool identification, MCP server detection, and vulnerability mapping, connecting identified tools to known vulnerabilities. It supports mapping detected vulnerabilities to frameworks like OWASP Top 10 LLM Applications and OWASP Agentic AI. Agentic Radar also offers advanced features such as Agentic Prompt Hardening to improve system prompts and the ability to test for vulnerabilities in agentic workflows through simulated adversarial inputs, including prompt injection and PII leakage.

LifeReloaded is an interactive life simulation game that leverages GPT-4's Advanced Data Analysis function to offer players a unique second chance at life. The game dynamically generates content in real-time, including character attributes, family backgrounds, MBTI personalities, and various life events. Players can make choices that influence their character's life path, with special events like encountering aliens or time travel adding unexpected twists. The Web version, powered by GPT-3.5-turbo, significantly reduces game content generation time to about 10 minutes and offers a more intuitive user interface. The project emphasizes the fusion of literature and AI, creating a rich narrative experience where every decision shapes the character's destiny, culminating in a unique epitaph.

Croduct PDF, despite its name, functions as an online gambling platform, specifically focusing on slot games from various providers. The platform is designed to be accessible across multiple operating systems including Android, iOS, Windows, macOS, and Linux, offering a seamless, app-like experience with fast loading times. It emphasizes security with features like Certificate Pinning and Biometric Authentication, and financial safeguards such as insurance from Lloyd's of London and client money protection. The platform boasts over 3,000 games from more than 50 providers, including baccarat, roulette, blackjack, and online football betting, with new games updated weekly. It also highlights its commitment to responsible gaming and ethical practices.

lamda is an advanced Android RPA agent framework designed for next-generation mobile automation. It integrates robust on-device services with AI-ready agents and extensible tool-calling capabilities, making it suitable for a wide range of automation tasks. The framework offers over 160 APIs for device discovery, status, logs, system and app control, UI automation, OCR, image matching, file I/O, storage, scheduling, and shell execution. It also includes built-in ADB/SSH/SCP, logging, API locking, and various utilities for production workflows. lamda supports stable automation across Android 6.0 to 16, including emulators and cloud phones, and runs non-intrusively without complex configuration. It also provides remote desktop and diagnostics features for visual monitoring and control.

TxAgent is an AI agent developed for precision therapeutics, focusing on generating personalized treatment recommendations. It employs multi-step reasoning and real-time biomedical knowledge retrieval, utilizing a comprehensive toolbox of 211 tools. The agent evaluates drug interactions at molecular, pharmacokinetic, and clinical levels, identifies contraindications based on patient comorbidities and concurrent medications, and tailors treatment strategies to individual patient characteristics like age, genetic factors, and disease progression. TxAgent retrieves and synthesizes evidence from multiple biomedical sources, assesses drug-patient condition interactions, and refines recommendations through iterative reasoning. It selects tools based on task objectives and executes structured function calls to solve complex therapeutic tasks requiring clinical reasoning and cross-source validation. The ToolUniverse integrates 211 tools, including all US FDA-approved drugs since 1939 and validated clinical insights from Open Targets. TxAgent is open-source and outperforms leading LLMs in drug reasoning and personalized treatment scenarios.

Youtu-Parsing is an AI-powered tool designed to analyze document images, including photos and scans, to identify and extract various elements. It excels at detecting layout components such as text, tables, and charts within documents. Users can upload their document images, and the tool will process them to extract readable information. This capability makes Youtu-Parsing highly valuable for automating data extraction and document analysis tasks, streamlining workflows that involve processing unstructured document data. Hosted on Hugging Face Spaces, it offers an accessible platform for document parsing needs.

Developers 360 is an AI and software development company that provides innovative technology solutions for businesses worldwide. They specialize in AI model tuning, precision web data collection, and workflow automation. The company offers services including web scraping, custom AI solutions for task automation, data analysis, and predictive insights, as well as comprehensive data solutions from scraping to display. Additionally, Developers 360 builds user-friendly, scalable websites and offers custom software development tailored to specific business needs. Their approach combines advanced technologies and tailored strategies to help organizations optimize processes, make informed decisions, and gain a competitive advantage.

Evebyte Studio, operating under the Atom.com brand, is a premium domain marketplace specializing in the sale of high-quality, brandable domain names. The platform ensures secure transactions by holding payments until the domain transfer is complete, guaranteeing buyer protection. It offers fast domain transfers, often within hours, and provides flexible payment options including full payment or installment plans. Evebyte Studio also features AI-powered naming contests, audience testing, and tools like a domain name generator and appraisal. While the specific 'Evebyte Studio' tool is not detailed, the website is focused on selling the 'EveByte.com' domain, which is described as ideal for cutting-edge tech startups in AI, fintech, or e-commerce.

🗣️ASR Clone Voice AI Gradio🔊 is an AI-powered voice cloning tool available on Hugging Face Spaces. It leverages Automatic Speech Recognition (ASR) technology to enable users to clone voices. While the tool's specific features beyond voice cloning are not detailed, its presence on a platform like Hugging Face suggests it is likely accessible for experimentation and development within the AI community. The current status indicates a build error, meaning it is not functional at this time.

Paddle-Lite is a high-performance, lightweight, flexible, and extensible deep learning inference framework designed for mobile, embedded, and edge hardware platforms. It is widely used within Baidu and by external users for production tasks. The framework supports models from PaddlePaddle, and offers an X2Paddle tool for converting models from other frameworks like Caffe, Tensorflow, and PyTorch. Key features include model optimization techniques such as quantization, subgraph fusion, and kernel selection, which result in lighter, faster, and more resource-efficient models. Paddle-Lite provides pre-compiled libraries for various platforms (Android, iOS, x86, macOS) and supports compilation from source. It offers C++, Java, and Python APIs with comprehensive examples for integration into diverse projects.

ToolOrchestra is an end-to-end Reinforcement Learning (RL) training framework designed to orchestrate tools and agentic workflows. It allows for the training of small orchestrators that efficiently coordinate the use of intelligent tools, surpassing larger models like GPT-5 in performance while being more efficient. The framework enables the Orchestrator to alternate between reasoning and tool calling in multiple turns, interacting with a diverse set of tools including web search, code interpreters, specialized LLMs, and generalist LLMs. Training is optimized through outcome, efficiency, and preference rewards via end-to-end reinforcement learning, supported by an automatic pipeline for synthesizing environment and tool-call tasks at scale. This framework has been used to produce Orchestrator-8B, a state-of-the-art 8B parameter model for solving complex, multi-turn agentic tasks.

ZhiLight is a highly optimized open-source LLM inference acceleration engine developed by Zhihu and ModelBest Inc. It is specifically designed to accelerate the inference of models like Llama and its variants, particularly on PCIe-based GPUs. The engine boasts significant performance advantages compared to other mainstream open-source inference engines such as vLLM and SGLang. Key features include an asynchronous OpenAI compatible interface, custom tensor and global memory management, encode and all-reduce overlap using "dual streams," and support for various quantization methods like Int8, SmoothQuant, FP8, AWQ, and GPTQ. ZhiLight also supports dynamic batching, flash attention prefill, prefix caching, and a wide range of models including Llama, Mixtral, and Qwen2 series.

Reach Best is an AI-powered application designed to assist high school students with their university applications. It provides tools and resources to help students navigate the college application process, including selecting universities, predicting admission chances, and writing application essays. The platform supports applications to universities in the USA, UK, Canada, Australia, and Japan, covering over 1,500 institutions worldwide. Key features include a Best-fit Bot for university matching, admission prediction, profile matching, and AI-assisted essay writing. Reach Best aims to reduce college application stress for students and empower them for university success, while also supporting counselors and teachers.

Kolby AI is a comprehensive sales performance system designed to enhance both inbound and outbound sales calls through real-time AI guidance. It offers features like in-call guidance, post-call coaching, and role-play training to help sales representatives improve their skills. The platform also includes a power dialer, transcription services, and supports over 70 languages. Kolby AI aims to close the gap between current performance and potential, enabling reps to achieve top closing skills and ensuring team consistency. It provides insights into sales temperature, preferred tone, next best actions, and handles objections effectively, ultimately leading to faster rep ramp-up times and improved overall sales performance.

DuckDuckGo MCP Server is a specialized AI tool hosted on Hugging Face Spaces, designed to integrate DuckDuckGo's search capabilities into AI agents and applications. Users can input a search query and receive a structured list of results, each containing a title, a direct link, and a concise summary. This server acts as an interface, allowing developers and AI agents to programmatically access and leverage DuckDuckGo's extensive search index. It is particularly useful for projects requiring real-time information retrieval from the web without building a custom search integration. The tool is currently paused on Hugging Face Spaces, requiring users to request its restart from the author(s).

MONTREAL.AI is a research company dedicated to the development and commercialization of artificial intelligence technology. Established in 2003, the organization strives to be at the forefront of the AI industry by engaging in the research and development of general-purpose AI technologies. While specific features or products are not detailed on the homepage, its core mission revolves around advancing the field of AI through scientific inquiry and innovation. The platform serves as a hub for information related to AI in Montreal, indicating a focus on regional and global contributions to the AI landscape.

mxnet-the-straight-dope is an interactive book focused on teaching deep learning, MXNet, and the Gluon interface through a series of Jupyter notebooks. It aims to combine prose, graphics, equations, and runnable code to create a comprehensive learning resource. The project emphasizes an open-source authorship process, welcoming community contributions. While much of its content has been incorporated into the Dive into Deep Learning Book available at d2l.ai, it still serves as a valuable, freely available resource for understanding deep learning fundamentals, convolutional neural networks, recurrent neural networks, optimization, and various applications in computer vision and natural language processing. It relies on MXNet for implementation, leveraging its speed and the Gluon imperative interface for research.

🔍RT-GPTW🏊 - Real Time ChatGPT Whisper is an AI tool designed for real-time conversational interaction, leveraging the power of ChatGPT and Whisper. This application allows users to engage with documents by uploading files and asking questions or providing instructions to receive detailed responses. Additionally, it offers audio transcription capabilities, enabling users to record audio and have it transcribed. All generated results, whether from document interaction or audio transcription, are saved, providing convenient access to past conversations and data. The tool is hosted on Hugging Face, making it accessible for various applications.

my_ml_service is a robust web service designed for deploying and managing machine learning models using Django. Unlike many other tutorials, this service focuses on making multiple ML models available at the same endpoint, supporting various versions simultaneously. It provides a REST API for easy integration and interaction with the deployed models. A key feature is its ability to store information about requests sent to the ML models, which is invaluable for model testing, auditing, and performance analysis. The service also includes built-in testing capabilities for both ML code and server code, and supports A/B testing between different versions of ML models to optimize performance and user experience. The project includes code for training models, simulating A/B tests, and Dockerfiles for containerized deployment.

The MCP-Chinese-Getting-Started-Guide is an open-source resource designed to introduce developers to the Model Context Protocol (MCP). MCP is an innovative open-source protocol that standardizes how large language models (LLMs) interact with the external world, enabling seamless access and processing of information from diverse data sources and tools. This guide focuses on implementing MCP servers, particularly for integrating tools like web search, and demonstrates how to develop MCP clients to interact with these servers. It covers practical examples using Python 3.11, uv for project management, and includes debugging with the Inspector visualization tool. The guide also delves into advanced features like Sampling, which allows for human supervision during tool execution, enhancing control and safety.

NagaAgent is a comprehensive agent framework designed for building personal AI assistants, offering intelligent interaction, multi-agent collaboration, and seamless tool integration. Key features include streaming tool calls, a knowledge graph memory system that automatically extracts and stores five-tuples from conversations into Neo4j, and Live2D virtual avatars for engaging user interaction. The framework also supports voice interaction through ASR, and integrates with various APIs including OpenAI compatible and Anthropic formats. NagaAgent allows for dynamic tool orchestration, self-configuration, and browser manipulation, making it a versatile platform for developers looking to create rich and interactive AI assistant experiences. It also includes unique features like game strategy assistance and a community forum.

Diip Artificial Intelligence specializes in developing custom AI solutions to drive digital transformation and optimize business processes. The company conducts thorough operational audits to understand specific client needs, then develops innovative AI solutions tailored to those requirements. Implementation is handled efficiently, either through API integration or by developing a user-friendly graphical interface. Diip AI aims to provide stability, advanced technology, personalization, speed, innovation, and productivity, with a vision to lead digital transformation through technology. They also offer specialized consulting, data analysis, and educational programs focused on AI for productivity.

Polymath Robotics specializes in developing core autonomy and safety systems specifically for off-highway vehicles. Their approach focuses on a software-first solution, aiming to simplify, accelerate, and reduce the cost of autonomy development for fleets. The system is designed to be both sensor-agnostic, allowing for customization with a wide range of sensors, and vehicle-agnostic, integrating with any size or type of off-highway machine. By keeping autonomy intelligence on the vehicle with onboard compute, it helps reduce networking costs. Polymath Robotics offers modular autonomy features, allowing users to select only the necessary components for their next-gen autonomy programs, ensuring flexibility and seamless integration.

ZeroGPU-LLM-Inference is a powerful AI tool hosted on Hugging Face Spaces, offering a streaming LLM chat experience. Users can type questions or requests and receive immediate, written responses from a language model. A key feature is the optional web-search integration, which pulls short snippets from DuckDuckGo to enrich the model's responses. The application also provides controls for customizing the chat experience, allowing users to tailor interactions to their specific needs. This makes it a versatile tool for various conversational AI applications, from quick information retrieval to more in-depth discussions powered by real-time web data.