AI Agents & Automation

Passisto is an AI-powered enterprise platform designed to revolutionize recruitment and knowledge management. It automates the entire hiring pipeline, from defining job offers and screening candidates at scale to conducting intelligent AI interviews and making data-driven decisions. The platform features automated CV screening, flexible phase management, AI interview templates, and automated communications to streamline the hiring process. Beyond recruitment, Passisto Enterprise includes a full suite of AI tools such as an AI Knowledge Base for unifying company documents, an AI Email Builder for generating context-aware emails, and an AI Form Builder for instant form creation. It aims to accelerate time-to-hire, enhance candidate quality, reduce recruitment overhead, and increase diversity and fairness in hiring.

ai-agents-from-scratch is a comprehensive educational resource designed to demystify AI agents by guiding users through building them from scratch. This repository emphasizes a hands-on approach, utilizing local LLMs and node-llama-cpp to provide a deep understanding of how agents function without relying on black-box frameworks. It covers fundamental concepts such as basic LLM interaction, system prompts, reasoning, parallel processing, streaming, function calling (tools), persistent memory, and advanced patterns like ReAct and Atom of Thought (AoT) planning. The resource includes detailed code examples, step-by-step explanations, and conceptual deep dives, making it ideal for developers who want to grasp the underlying mechanisms before engaging with production frameworks.

Bulk Rename Utility is an intelligent solution for automated file renaming, leveraging advanced AI technology and customizable rule-based operations. This free online tool allows users to transform their file organization effortlessly on both Windows and Mac platforms, without requiring any installation. It supports smart batch renaming capabilities, offering AI-driven suggestions for efficient file management. The utility ensures user privacy by performing all operations locally, meaning files and folders are imported and processed on the user's device without being uploaded. This makes it a secure and versatile tool for anyone needing to manage large volumes of files with precision and ease.

Leon is an open-source personal AI assistant built around tools, context, memory, and agentic execution. Designed for practicality and privacy, it can operate locally, leveraging dedicated tools instead of relying on free-form guessing to complete tasks. Leon supports both deterministic workflows and agent-style execution, allowing it to understand goals, choose how to handle them, and recover from errors. It integrates with local and remote AI providers, balancing privacy, control, and capability. The core architecture organizes capabilities into Skills, Actions, Tools, and Functions, with a compact self-model and proactive pulse system for consistency. It's ideal for users who prioritize privacy and grounded, extensible AI assistance.

OpenPipe is an AI tool designed to optimize AI models and enhance developer efficiency, particularly for those working with Reinforcement Learning (RL) for agents. It focuses on improving AI workflows and streamlining the development process through seamless integration capabilities. The platform aims to provide robust solutions for building and managing AI agents, ensuring high-quality output and efficient operation. OpenPipe supports developers in creating more effective AI systems by offering tools that simplify complex RL implementations and integrate smoothly into existing development environments. This focus on optimization and integration makes it a valuable asset for developers looking to push the boundaries of AI agent performance.

Runbear is an AI agent platform designed to automate Slack inboxes for operations, customer success, and RevOps teams. It integrates with over 2,000 tools, including Notion, Linear, HubSpot, and Google Drive, to pull answers and take action directly within Slack, Microsoft Teams, and HubSpot. The platform acts like a teammate, understanding context, answering questions, routing inquiries, creating tickets, and updating CRMs without requiring users to leave their communication platforms. Runbear learns from team interactions and existing documentation, getting smarter with every conversation. It boasts a quick 10-minute, no-code setup, allowing users to connect tools and invite Runbear to channels easily. Security features include SOC 2 Type II compliance, SSO, RBAC, and data encryption, ensuring data safety and privacy.

Rea is a conversational AI agent developed by Cenango, designed to streamline business operations through intelligent automation. This AI agent seamlessly handles complex enterprise workflows, reducing response times and boosting efficiency by managing routine tasks. It maintains perfect context throughout every interaction, ensuring customers receive accurate and relevant responses, and continuously improves its performance by learning from each conversation. Rea integrates smoothly with existing systems and tools, offering 24/7 availability to answer calls, qualify leads, and book appointments, allowing teams to focus on strategic initiatives and closing deals. It also analyzes calls, scores leads, and creates summaries to track performance and improve conversions in real time.

Wyr.AI Private Limited provides an innovative AI-powered solution for visual quality inspection across various industries. This tool enables a hands-free, automated process to detect defects, ensuring precise scanning and improved efficiency for quality assurance teams. It eliminates human error and bias, offering features like live inspection monitoring and automated reports. Wyr.AI is particularly effective for inspecting textiles, identifying issues like stains, holes, and uneven stitching; toys, checking for loose parts and sharp edges; apparel, detecting fabric imperfections and faulty stitching; handicrafts, assessing intricate details; artificial jewelry, analyzing designs and gem settings; and hard goods, identifying scratches, dents, and misalignments. The platform aims to reduce costs and enhance product reliability by performing over 50 quality checks in just a minute.

Quansys AI focuses on developing the next generation of Business Process Outsourcing (BPO) infrastructure through advanced AI agents. The platform leverages swarm intelligence to create full-stack AI call centers, automating various business processes. This includes the deployment of voice AI agents, all running on robust cloud infrastructure. Quansys AI envisions a future where BPO operations are entirely automated, minimizing or eliminating the need for human intervention. This approach aims to enhance efficiency, reduce operational costs, and provide scalable solutions for businesses looking to modernize their customer service and operational workflows.

YVI is an AI-powered talent acquisition and HR management platform designed to streamline and simplify the entire hiring process. It features an AI-based video interview platform for efficient candidate assessment and intelligent resume shortlisting to quickly identify best-fit candidates. Beyond recruitment, YVI offers a comprehensive People Suite for HRMS, covering core HR functions like attendance, payroll, employee experience, and compliance. The platform emphasizes fairness and bias monitoring through Agentic AI, ensuring objective candidate evaluations. With robust reporting, diversity analytics, and secure data handling, YVI aims to free HR professionals to focus on employee engagement and strategic initiatives.

AITinerary is an AI-powered trip planner designed to simplify travel planning by generating personalized itineraries. Users can describe their dream trip, and the AI will create a complete plan, including suggestions for flights and discovering hidden gems. The tool is great for personalized travel itineraries and discovery, offering options like foodie tours focusing on local street food and fine dining, cultural exploration of historical landmarks and traditions, and nature-focused trips to find the best spots for hiking, beaches, and scenic views. It aims to make trip planning effortless and efficient.

Glow Baby is a comprehensive AI-powered mobile application designed to assist parents in meticulously tracking their baby's essential activities. It allows users to log feeding schedules, sleep patterns, diaper changes, and developmental milestones, offering a holistic view of the baby's daily routine. The app leverages AI to provide personalized insights and forecasts, helping parents understand their baby's unique patterns and make informed decisions about their care. A key feature is the support for multiple caregivers, fostering collaborative baby care among family members or nannies. This collaborative functionality aims to reduce parental anxiety by ensuring all caregivers are aligned and have access to the same up-to-date information. Glow Baby is part of the larger Glow ecosystem, which includes apps for period tracking, ovulation, and pregnancy, offering a continuous health guide from conception through early parenting.

MaxText is a high-performance, highly scalable, open-source library for Large Language Models (LLMs), implemented in pure Python/JAX. It is designed to run efficiently on Google Cloud TPUs and GPUs, supporting both pre-training and scalable post-training with techniques like Supervised Fine-Tuning (SFT) and Reinforcement Learning (GRPO, GSPO). MaxText achieves high Model FLOPs Utilization (MFU) and tokens/second across various cluster sizes, leveraging the power of JAX and the XLA compiler. It offers a library of high-performance models including Gemma, Llama, DeepSeek, Qwen, and Mistral, and serves as a launching point for ambitious LLM projects in research and production. Users can experiment with MaxText out of the box or fork and modify it to meet specific needs, with support for multi-modal training.

AIBrix is an open-source initiative designed to provide essential building blocks for constructing scalable GenAI inference infrastructure. It delivers a cloud-native solution optimized for deploying, managing, and scaling large language model (LLM) inference, tailored specifically to enterprise needs. Key features include high-density LoRA management, an LLM Gateway and Routing for efficient traffic direction, and an LLM App-Tailored Autoscaler for dynamic resource scaling. It also offers a Unified AI Runtime, distributed inference capabilities, distributed KV cache for high-capacity reuse, and cost-efficient heterogeneous serving with SLO guarantees. AIBrix further includes GPU hardware failure detection for proactive issue identification.

AIClient-2-API is a powerful API proxy service designed to unify and simulate requests for various client-only large language models, including Gemini CLI, Antigravity, Codex, Grok, and Kiro. It encapsulates these into a local OpenAI-compatible interface, allowing any application to connect easily. Built on Node.js, it intelligently converts between OpenAI, Claude, and Gemini protocols, enabling tools like Cherry-Studio and NextChat to utilize advanced models such as Claude Opus 4.5 and Gemini 3.0 Pro at scale. The project features a modular architecture with account pool management, intelligent polling, automatic failover, and health checks, ensuring high service availability. It also offers a Web UI management console for real-time configuration and monitoring.

Nsfw is an AI-powered image classification tool available as a Hugging Face Space. Users can upload an image, and the application will analyze it to determine its content category. The tool provides probabilities for various classifications, including drawings, hentai, neutral, porn, and sexy. This functionality is useful for content moderation, filtering, or simply understanding the nature of visual media. Being hosted on Hugging Face, it offers an accessible and straightforward way to perform NSFW content detection without complex setup.

Chatmosphere is an innovative platform designed to generate personalized chat rooms based on user descriptions. It allows for the creation of custom characters, enabling interactive experiences such as 'Choose Your Own Adventure' stories. The platform leverages OpenAI's technology to craft engaging and dynamic conversational environments. A key feature is the privacy of user chats, which are stored locally on the user's device, ensuring data security. This tool is ideal for individuals looking to explore creative storytelling, role-playing, or simply interact with AI-generated personalities in a private setting.

SQWK is an AI-powered tool designed for serious Microsoft Flight Simulator pilots, offering airline-grade post-flight debriefs for MSFS 2024 and MSFS 2020. It captures each approach from final to rollout, transforming landings into structured debriefs with trend context, runway and weather factors, and a clear correction for the next session. The platform analyzes the build-up, flare, touchdown window, and rollout, providing context such as aircraft, runway, wind, and recent baseline performance. Each debrief concludes with a specific practice focus rather than just a score, helping pilots improve their skills. SQWK Linker captures flight data, telemetry, and runway-phase context, ensuring comprehensive analysis. The dashboard highlights the next flight focus, maintains a continuous flight log, and offers procedural coaching for targeted improvement.

EscortBot is an AI chatbot hosted on Hugging Face that offers simulated conversations with a character named Amber, designed to be a flirtatious escort. The application allows users to text Amber, who responds in a short and enticing manner with the goal of setting up dates. Conversation logs are saved locally, providing a continuous interaction experience. This tool is presented as an entertainment-focused AI agent, built with Gradio and available for free use on the Hugging Face platform. It is licensed under the MIT license, indicating its open-source nature.

AI Toolkit is a comprehensive and easy-to-use open-source training suite specifically designed for finetuning diffusion models. It supports a wide array of image and video models, including popular ones like FLUX, SDXL, and various Wan-AI video models. The toolkit offers flexibility, allowing users to interact with it via a graphical user interface (GUI) or a command-line interface (CLI). It is optimized to run effectively on consumer-grade hardware, making advanced model training accessible. Key features include support for LoRA and LoKr training, detailed configuration options for specific layer training, and integration with platforms like RunPod and Modal for cloud-based training. The project is free and open source, emphasizing ease of use while providing extensive features for diffusion model development.

HowToReplyTo is an AI-powered tool designed to generate creative and unique replies to messages across diverse contexts, including family, friends, dating, and professional communications. Users input a message, select the recipient type (e.g., Tinder/Dating, Friends, Family, Professional), choose a desired response tone (e.g., Funny, Rude & Angry, Emotional), and apply additional filters like slang or cultural context. The AI then generates several personalized reply options. This tool aims to improve communication by providing context-specific, emotion-based, and culturally aware suggestions, making it easier to craft engaging and appropriate responses for any situation.

GPT-Vis is an AI-native visualization library specifically designed for the LLM era, offering a framework-agnostic solution for AI-powered applications. It provides over 20 chart types, including statistical, relationship, and advanced visualizations, all generated with a simple, markdown-like syntax that LLMs can effortlessly create. Key features include streaming support for AI model output, fault tolerance for incomplete data, and intelligent defaults for automatic data detection and adaptive layouts. The tool also boasts a comprehensive knowledge base to guide LLMs in selecting appropriate chart types and data structures, evaluated with over 90% accuracy across 200+ scenarios. It supports integration with vanilla JavaScript, React, and Vue.

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.

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.