AI Agents & Automation

Fume is an AI testing tool designed to automate end-to-end browser testing by acting as an autonomous QA team. Users record a Loom-style video describing what they want to test, and Fume generates and maintains Playwright tests. It extracts test cases in seconds, covering major user flows quickly. Fume offers self-healing tests with AI agent fallbacks for Playwright's fragility, ensuring tests continue even if scripts break. It provides free test runners in the cloud and allows full ownership of the generated Playwright code, which can be run locally or integrated into existing CI/CD pipelines. Fume also supports migrating existing Playwright, Selenium, or Cypress tests.

EmailCrafted is an AI-powered email writing tool designed for professionals to generate personalized and professional emails in seconds. It allows users to customize the tone, structure, and brand voice of their communications. The platform offers flexible email solutions for diverse needs, including business communication, client outreach, and follow-up messages. EmailCrafted streamlines hiring processes, ensures consistent customer support responses, and helps build a strong brand presence through polished email communication. Users can register their brand voice by uploading an existing email or inputting key details, then simply enter recipient information and desired tone to generate a ready-to-send email.

golearn is a comprehensive machine learning library designed for the Go programming language, emphasizing both simplicity and customizability. It offers a 'batteries included' approach, providing a wide range of functionalities for machine learning tasks. Users can load data as Instances, perform matrix-like operations, and pass them to various estimators. The library implements the scikit-learn interface of Fit/Predict, allowing for easy swapping of estimators during trial and error. Additionally, golearn includes helper functions for data management, such as cross-validation and train-test splitting. It supports various algorithms including KNN, linear models, neural networks, and decision trees, making it suitable for diverse machine learning applications.

Agent File (.af) is an open standard file format designed for serializing stateful AI agents. Originally developed for the Letta framework, it provides a portable method for sharing agents that retain their persistent memory and behavior. This format packages all essential components of a stateful agent, including system prompts, editable memory (personality and user information), tool configurations (code and schemas), and LLM settings. By standardizing these elements, Agent File facilitates seamless transfer between compatible frameworks, enabling easy checkpointing and version control of agent states. It addresses the need for a common standard in the rapidly growing AI agent development ecosystem, promoting portability, collaboration, preservation, and versioning of AI agents.

Intent is a public beta desktop application designed as a developer workspace for AI agent orchestration. It enables spec-driven development, allowing users to plan, execute, and iterate on complex coding tasks with the assistance of AI agents. The tool is currently available for macOS (Apple Silicon). This platform aims to augment code development by providing a structured environment where AI agents can assist throughout the coding lifecycle, from initial planning to execution and refinement. It's built to streamline the development process for complex projects, offering a new approach to how developers interact with AI in their daily workflows.

Mario-GPT is an open-source AI tool designed for generating Super Mario levels using a finetuned GPT2 model. Trained on levels from Super Mario Bros and Super Mario Bros: The Lost Levels, it allows users to create new game environments guided by simple text prompts. While the generation may not be perfect, it represents a significant step towards more controllable and diverse level generation. The tool provides code snippets for generating levels, continuing generation, and interacting with generated levels through interactive play or an Astar agent. It also includes training code for those interested in further development and offers a Huggingface demo for interactive use without needing local GPU resources.

CareerGenie is an AI-powered recruiting platform designed to significantly boost the capacity of fast-growing teams, talent agencies, and startups. It automates the entire candidate sourcing and screening process, from defining roles and creating job pages to discovering high-fit candidates across millions of profiles. The platform conducts AI-led interviews 24/7, providing detailed transcripts and clear signals to generate a ranked shortlist of top candidates. This allows human recruiters to focus on high-stakes conversations and final interviews, rather than tedious search, outreach, and initial screening tasks. CareerGenie aims to provide instant recruiting capacity, deeper candidate insights beyond resumes, and faster hiring decisions without increasing headcount.

DigiTele Networks, established in 2005, is a global organization providing a wide array of IT services with a strong focus on the renewable energy sector. Their core offering includes 'intellaire', an AI/ML-powered drone solutions platform for efficient and economical inspections. They specialize in industrial drone inspections for solar PV modules, wind turbines, oil & gas pipelines, and 3D aerial mapping. Beyond drone services, DigiTele Networks also provides IT services such as mobile app development, UX design, startup mentoring, and business process outsourcing. With over 10 years of experience in the energy industry, they have completed drone-based IR thermography across numerous locations in India, inspecting over 3.5GW+ solar capacity and 1.25Crore+ PV modules.

Xandidate redefines the hiring process by leveraging AI to classify candidates precisely based on job descriptions. It trains a unique AI for each company job, ensuring bespoke matching. This platform transforms recruitment with intelligent candidate matching, automated screening, and data-driven insights. Key features include AI-powered candidate matching, automated screening, AI-optimized job descriptions, and bias reduction. It aims to reduce time-to-hire by 60% and improve hire quality, making it ideal for HR professionals and recruitment managers looking to streamline their hiring workflows.

Intemic is an operational intelligence platform designed for industrial operations and engineering teams. It unifies industrial data, AI agents, automations, and reporting into a single, comprehensive platform. The tool empowers users to understand, predict, and optimize complex industrial processes in real-time, leading to reduced waste, fewer failures, and lower costs while maintaining product quality. By leveraging AI, Intemic helps industrial companies unlock the value of their data to improve overall operational efficiency and decision-making.

Weddy is the #1 AI wedding planner app designed for couples to effortlessly plan their dream wedding. Available on iOS and Android, it provides a comprehensive suite of AI-powered tools including budget tracking, guest management, and personalized RSVP websites. The app also features AI assistants that offer personalized suggestions for venues, optimize budgets, and answer wedding planning questions. Couples can collaborate in real-time with their partners, manage tasks, and make decisions together. Weddy offers a free plan for smaller celebrations and a Premium plan for unlimited features, AI assistants, and customizable RSVP websites, ensuring a stress-free and organized planning experience.

Fin-R1 is a specialized large language model designed for complex financial reasoning, developed through a collaboration between SUFE-AIFLM-Lab at Shanghai University of Finance and Economics and FinStep.AI. Built upon the Qwen2.5-7B-Instruct base model, Fin-R1 undergoes a two-stage training process involving supervised fine-tuning (SFT) and reinforcement learning (RL) using high-quality, verifiable financial data. This approach enables it to achieve state-of-the-art performance across various financial benchmarks, including financial code generation, calculations, security compliance, smart risk control, and ESG analysis. The model is lightweight at 7B parameters, making it cost-effective to deploy while providing robust support for core financial business scenarios in banking, securities, insurance, and trusts.

The AUTONOMOUS AI RESEARCH LAB offers a unique platform where self-improving AI agents conduct experiments to advance AI knowledge. Users can sign in to an exclusive dashboard to observe and potentially interact with these autonomous systems, pushing the boundaries of machine learning. The platform is designed for those interested in the cutting edge of AI development, providing a window into the processes of AI experimentation and self-improvement. While the current website primarily features a login portal, the core concept revolves around providing access to an environment where AI can evolve and generate new insights.

AI Strategy Corporation, through its 9-HI platform, offers a patent-pending technology for Human-AI collaborative Decision Guidance. This platform is designed to enhance success in commercialization by integrating project management, innovation management, knowledge management, risk management, and state-of-the-art Human and AI collaboration. It aims to drive product or technology success, funded by entities like the US Air Force and OUSD Defense Production Act. 9-HI helps organizations make more informed decisions on technology investments, providing a standard process for technology acquisition and development. The platform utilizes AI Agents like Orion, Scorpius, Cassiopeia, Hercules, and Libra to assist with subject matter expertise, risk identification, success factors, solution options, and success evidence, feeding into a Success Probability Scoring Engine.

Navana.ai is building India’s foundational voice AI infrastructure with proprietary speech models that understand India, not just linguistically, but contextually across 12 Indian languages and 40+ dialects. Their Bodhi speech models are purpose-built for Indian realities, handling real-world audio challenges like noise, overlaps, code-switching, and accents. The platform offers an end-to-end voice AI stack engineered for pan-India scale, complexity, and compliance, with enterprise-grade performance. Navana.ai provides solutions like an AI Contact Center, Bodhi Speech API for real-time and batch use cases, and an Audio Intelligence API for call center automation, delivering transcripts, summaries, and performance insights. It is designed for enterprise needs, offering on-prem architecture for data control and security, seamless integrations, and compliance with RBI guidelines, ISO 27001, and SOC 2 Type II standards.

Awesome-LLM4IE-Papers is a valuable open-source resource hosted on GitHub, dedicated to compiling academic papers focused on generative Information Extraction (IE) using Large Language Models (LLMs). The repository is organized based on a comprehensive survey titled "Large Language Models for Generative Information Extraction: A Survey," which also serves as a guide to the paper organization. It categorizes papers by specific IE tasks such as Named Entity Recognition, Relation Extraction, and Event Extraction, as well as by techniques like Supervised Fine-tuning, Few-shot learning, and Prompt Design. Researchers and practitioners can find recently updated papers, datasets with download links, and contribute suggestions or corrections via email. This resource is essential for staying current with advancements in LLM-driven information extraction.

Ora AI, formerly Synaptiq, is an AI-powered learning platform designed to simplify medical school studies. It offers an evidence-based study platform that guides students from their first year (M1) through to becoming an MD. The platform is designed by top doctors and educators and is loved by over 24,000 students. Users praise Ora AI for its ability to identify weaknesses and create a structured plan to address them, acting as a blend between UWorld and Anki. It leverages AI to determine what students need to study, allowing them to focus on practice questions without having to plan their study regimen.

Gryfo offers a robust facial recognition platform designed for seamless integration into existing technological solutions. Leveraging deep learning and computer vision, it provides offline facial recognition capabilities, making it suitable for diverse applications such as employee time tracking, secure online payments, and identity verification through face matching and liveness detection. The platform offers both API and SDK options, supporting various development needs across different scales, from small businesses to large corporations. Gryfo emphasizes high scalability, accuracy, and fraud prevention, with features like liveness detection and multi-platform support. It aims to make AI accessible, helping businesses innovate and expand their customer base.

SLAM-LLM is a comprehensive deep learning toolkit designed for researchers and developers to train custom multimodal large language models (MLLMs). It specializes in processing speech, language, audio, and music, offering detailed recipes for training and high-performance checkpoints for inference. The framework supports multi-task training, dynamic prompt selection, and iterative datasets for large-scale industrial applications, including datasets on the order of 100,000 hours. Key features include DeepSpeed training for reduced memory usage, multi-machine multi-GPU inference, and dynamic frame batching to significantly reduce training and evaluation times. It also provides flexible configuration options based on Hydra and dataclass, allowing for a combination of code, command-line, and file-based configurations.

Grpo Vlm Decoder is a VLM-based message decoder, specifically trained using the GRPO (Gradient-based Reinforcement Learning for Policy Optimization) method. Hosted on Hugging Face Spaces, this tool is freely accessible and built with Gradio, making it suitable for various applications in natural language processing. While the live website currently shows a build error, its intended purpose is to provide a platform for research, development, and educational exploration of VLM decoding techniques. It offers a practical example of applying advanced machine learning models to message interpretation tasks.

Ab(new)normal AI is a disruptors venture studio focused on helping global businesses leverage Artificial Intelligence and Blockchain for growth. They work with high-impact, entrepreneurially-minded business leaders to move from idea to execution at speed, simplifying and solving globally relevant complex problems. The company achieves this by fostering an innovation-nurturing culture, utilizing M&A and IP commercialization, and applying AI and other exponential technologies like fintech, IoT, and metaverse/AR/VR to design and build new ventures. Their services include formulating disruption strategies, building and launching ventures, fundraising, commercializing IP, fostering an internal culture of innovation, and providing innovation advisory and executive coaching.

Navan AI is an autonomous AI development platform designed to transform Product Requirements Documents (PRDs) into production-ready, tested code. It leverages a Smart Agent Manager (SAM) to orchestrate specialized AI agents through strict Test-Driven Development (TDD) cycles, ensuring quality software delivery without direct human intervention. The platform features a TDD pipeline with RED-GREEN-REFACTOR methodology, where agents like Titan (Test Architect) write failing tests, Dyna (Developer) implements code to pass them, and Argus (Code Reviewer) refactors. SAM acts as the master orchestrator, managing state and enforcing quality gates. Key benefits include autonomous execution, guaranteed TDD enforcement, built-in quality gates, state tracking, smart retries, and automatic documentation generation, accelerating software delivery with built-in quality.

iVoz Ai offers an advanced AI Voice Agent designed to empower businesses across various sectors by automating lead generation and customer interactions. This tool enables instant AI voice agents and real-time solutions, redefining business communication. It integrates seamlessly with existing CRM systems, ensuring a smooth and hassle-free experience. iVoz Ai helps businesses save up to 70% on costs by only charging for answered calls, making it a cost-effective solution for acquiring superior leads. The platform supports multilingual interactions with auto language detection and industry-specific vocabulary, catering to diverse customer bases in industries like real estate, insurance, financial services, healthcare, and education.

snake-ai is an open-source project featuring an AI agent designed to master the classic game "Snake." The agent is trained using deep reinforcement learning, offering two distinct versions: one based on a Multi-Layer Perceptron (MLP) and another utilizing a Convolutional Neural Network (CNN). The CNN-based agent demonstrates superior performance, consistently achieving higher average game scores. The project provides program scripts for the game itself, along with trained models for both AI versions, allowing users to test and observe their performance. It also includes scripts for retraining models and viewing training process curves via Tensorboard, making it a valuable resource for those interested in practical applications of deep reinforcement learning in gaming.