AI Agents & Automation

OmniMind's Omnitable transforms basic data tables into powerful AI-powered assistants, automating sales and marketing processes. Users can import data from various sources like Google Sheets, HubSpot, and Apollo, then add AI columns to research, enrich leads, push data to CRMs, generate personalized content, send emails, or analyze patterns. Each AI column acts as a smart agent, allowing teams to scale effortlessly without extra costs. It helps cut down on manual tasks, provides 24/7 support, and streamlines workflows for lead generation, data research, and outreach. Omnitable is designed for simplicity and speed, enabling users to set up instructions in plain text.

OpenSandbox is a robust, open-source sandbox platform designed for AI applications, offering a secure, fast, and extensible runtime environment for AI agents. It provides multi-language SDKs in Python, Java/Kotlin, JavaScript/TypeScript, C#/.NET, and Go, along with unified sandbox APIs. The platform supports both Docker and high-performance Kubernetes runtimes, enabling local execution and large-scale distributed scheduling. OpenSandbox is ideal for scenarios such as Coding Agents, GUI Agents, Agent Evaluation, AI Code Execution, and RL Training. It features strong isolation with secure container runtimes like gVisor and Firecracker microVM, and includes built-in Command, Filesystem, and Code Interpreter implementations.

Paper2Agent is an innovative multi-agent AI system designed to automatically convert research papers into interactive AI agents. This system requires minimal human input, streamlining the process of transforming complex research into actionable AI tools. It intelligently identifies and executes relevant tutorials directly from a research paper's associated codebase, enabling users to interact with the paper's methodologies and findings in a dynamic way. Paper2Agent supports both basic and advanced usage, allowing for targeted tutorial processing and integration with API keys for authenticated repositories. The system generates a comprehensive project structure including an isolated Python environment, extracted tools, and detailed reports on code coverage and quality, making it a robust solution for researchers and developers.

Opik, built by Comet, is an open-source platform designed to streamline the entire lifecycle of LLM applications, from prototype to production. It empowers developers to evaluate, test, monitor, and optimize their models and agentic systems with comprehensive tracing of LLM calls, conversation logging, and agent activity. Key features include advanced evaluation capabilities like LLM-as-a-judge for tasks such as hallucination detection and RAG assessment, experiment management, and integration into CI/CD pipelines. Opik also offers production-ready scalable monitoring dashboards, online evaluation rules, and dedicated SDKs for prompt and agent optimization, along with guardrails for safe AI practices. It supports a wide array of frameworks and offers client SDKs for Python, TypeScript, and Ruby.

Ragworks AI offers an autonomous sales development rep (SDR) that streamlines the entire outbound sales process. It automatically finds and verifies prospects, crafts hyper-personalized outreach messages using recent news and company context, handles replies, and books qualified meetings. The platform integrates with CRMs like HubSpot and Salesforce, and supports multi-channel outreach including LinkedIn, Email, Calendar, WhatsApp, and Phone. Ragworks AI aims to replace manual SDRs, offering a significant cost reduction while booking more qualified meetings. It also features a 'Playground' for testing campaigns and an AI Strategist Layer for continuous optimization of playbooks and messaging, ensuring a high-performing outbound engine.

Onepanel is an open-source, end-to-end computer vision platform designed to streamline the entire computer vision lifecycle. It provides a unified environment for labeling datasets, building models, training, tuning hyperparameters, deploying, and automating computer vision workflows. The platform is built to be flexible, supporting deployment on any cloud infrastructure as well as on-premises environments. By integrating various open-source projects like Argo, Couler, CVAT, JupyterLab, and NNI, Onepanel offers a comprehensive solution for machine learning and deep learning practitioners. It aims to simplify complex computer vision tasks from data preparation to model deployment and automation.

10x.Team is an AI-powered talent execution engine designed to supercharge recruiting efforts by automating key stages of the hiring process. It allows users to generate job descriptions, select from over 50 AI recruiters in 70+ languages to conduct screening and first-round interviews, and reclaim significant recruiter time. The platform offers features like RoleCraft for AI briefing and knock-out questions, TrueTalk for configuring AI recruiter avatars, voices, and interview tones, and HireRank for unbiased candidate ranking with video replays. 10x.Team aims to provide a fast, fair, and compliant AI recruiting experience, reducing bias and allowing hiring managers to focus on more strategic tasks. It offers flexible pricing, including a free tier for initial testing.

ASENSEI is a leading software development kit (SDK) that leverages computer vision for movement recognition and AI coaching intelligence. It enables businesses to transform workout videos into personalized experiences, offering guidance, adaptation, and rewards to boost customer acquisition, engagement, and retention in fitness. In healthcare, ASENSEI assists in onboarding patients into virtual physical therapy, providing real-time support, tracking progress, and ensuring adherence. This technology helps improve patient outcomes, reduce care costs, and facilitate scalable, high-quality treatment. ASENSEI.AI simplifies the integration of motion capture, movement recognition, and AI coaching into any hardware or software product, providing the 'brain' for AI coaches with cutting-edge computer vision and specialized large language models.

AgentPayment offers a robust payment SDK designed specifically for autonomous AI agents, allowing them to transact with each other without human intervention. This innovative platform supports a hybrid payment network, integrating crypto (ETH on Base Mainnet) and traditional fiat rails (Stripe card and ACH) into a single SDK. Key features include Agent-to-Agent (A2A) billing with auto-approval rules, accountless payments for external agents, and partial/installment payment options with automatic retries. The system is 100% non-custodial, ensuring funds flow directly between agents. It also provides real-time webhooks for instant event notifications, multi-agent support with isolated API keys, and enterprise-grade security features like API key authentication and audit logging. AgentPayment is built for the agentic economy, offering a comprehensive solution for machine-to-machine payments.

PhiFlow is an open-source simulation toolkit designed for machine learning and optimization, primarily written in Python. It offers a differentiable PDE solving framework that seamlessly integrates with popular machine learning frameworks such as NumPy, PyTorch, Jax, and TensorFlow. This integration allows users to leverage automatic differentiation for building end-to-end differentiable functions that combine learning models with physics simulations. PhiFlow supports a wide range of applications, particularly in fluid dynamics, with features like built-in PDE operations, a flexible web interface for live visualizations, and object-oriented design for extensibility. It enables reusable simulation code across different backends and dimensionalities, making it a versatile tool for researchers and developers.

Brain4Industry is a scientific-industrial consortium dedicated to enhancing the competitiveness of small and medium-sized manufacturing enterprises in the Czech Republic. It achieves this by facilitating the adoption of innovative digital solutions, additive manufacturing systems, and artificial intelligence. The consortium offers a comprehensive suite of services including digitalization and AI consulting, digital twin development, AI data management, and AI production assistance for R&D. Additionally, Brain4Industry provides expertise in AM research and product development, mechanical design, mathematical simulations, VR/AR applications, and prototyping. The platform also offers educational programs, financial consulting, and support for ESG reporting, acting as a one-stop shop for businesses seeking to integrate advanced technologies and improve sustainability.

Bagoodex provides an online AI chat experience, functioning as both an AI chatbot and an AI chat generator. Users can leverage the platform to search for information, generate written content, and create images instantly. The tool emphasizes a fast, flexible, and intelligent interaction, aiming to enhance information retrieval and content creation through its AI capabilities. The website indicates a recent update, including a new domain and refreshed features, with a prompt to "Move to Sigma AI," suggesting a rebranding or migration.

Python-ai-assistant, also known as Jarvis, is an open-source voice-commanding AI assistant built with Python 3.8. It offers a range of functionalities including speech recognition, text-to-speech interaction, and the execution of various commands. Users can interact with Jarvis via voice or text to perform tasks such as opening web pages, playing music, checking weather, setting alarms, and performing basic calculations. The assistant supports asynchronous command execution and allows for easy customization of voice commands and configurable assistant names. It also keeps a history of commands and learned skills in MongoDB, making it a versatile tool for personal automation.

DocDraft is an AI-powered platform designed to simplify legal document drafting and provide access to expert legal guidance. Users can leverage AI to generate attorney-grade documents, including lease agreements, contracts, LLC documents, and more, with guided intake to capture essential facts. The platform also offers human expertise through licensed attorneys who provide personalized review, strategy, and custom edits. DocDraft aims to reduce overhead and bundle repeatable work, ensuring users pay for expertise rather than inflated billable hours. It caters to individuals and small businesses, offering ongoing support and various subscription plans to suit different legal needs, from specific questions to complex matters.

gpt-home is an open-source project that allows users to build their own ChatGPT-powered smart home assistant using a Raspberry Pi. It serves as a customizable alternative to commercial smart home devices like Google Nest Hub or Amazon Alexa. The project provides a comprehensive guide and all necessary components to set up the system, integrating with various services such as OpenAI, Spotify, Philips Hue, and OpenWeatherMap. It supports use cases like weather updates, alarms, reminders, calendar management, general knowledge queries, translation, music control, and smart lighting. The system is built with LiteLLM and LangGraph, ensuring persistent memory and display support, and is designed to run on any Linux system with Docker.

PyTorch Frame is a modular deep learning framework built upon PyTorch, specifically designed for heterogeneous tabular data. It supports various column types including numerical, categorical, text, time, and images, enabling the creation of sophisticated neural network models. The library provides a flexible architecture for implementing existing and future deep learning methods, featuring state-of-the-art models, user-friendly mini-batch loaders, and benchmark datasets. It also facilitates integration with diverse model architectures, including Large Language Models, allowing users to encode text data with embeddings and train alongside other complex semantic types. PyTorch Frame aims to democratize deep learning research for tabular data, making it accessible for both novices and experts.

Viff is an AI-powered assistant designed to streamline the process of responding to guest reviews, helping businesses maintain a strong online reputation. It ensures that no customer feedback goes unanswered by automating and customizing responses. The tool integrates with multiple platforms, including email, and allows users to tailor replies based on their business profile and brand voice. Viff offers unlimited replies and rewrites, providing flexibility and consistency in customer communication. This makes it an ideal solution for businesses looking to efficiently manage their online presence and customer interactions.

Cloudsquid is an AI agent designed for finance and operations teams, automating complex end-to-end workflows across various systems like ERPs, portals, email, and spreadsheets. Users can upload Excels, PDFs, and data exports, describe their needs, and receive auditable results. The platform offers features such as automated cash application, invoice processing, spend classification, deduction analysis, and master data cleanup. It provides enterprise-grade security with ISO 27001 certification, SOC II compliance, GDPR adherence, and zero data retention. Cloudsquid aims to increase team capacity by handling reconciliations, cleanups, and audits, providing a full audit trail with tracked edits, cited sources, and reviewable decisions.

redis-inference-optimization is a Redis module designed for serving tensors and executing deep learning graphs. Previously known as RedisAI, this tool acts as a "workhorse" for model serving, offering support for popular Deep Learning and Machine Learning frameworks such as PyTorch, TensorFlow, TensorFlow Lite, and ONNXRuntime. It maximizes computation throughput and reduces latency by adhering to data locality principles, while simplifying the deployment and serving of graphs through Redis's robust infrastructure. Although the project is no longer actively maintained or supported, it provides a valuable reference for integrating AI inference capabilities directly within a Redis environment. Users are directed to the Redis website for current AI offerings.

Delta Bravo AI specializes in building agentic AI systems tailored for highly regulated industries, including water utilities, wastewater management, and environmental compliance. Their suite of products, Data Mentor, Aquaspec, and PermitPro, are designed to address critical bottlenecks in these sectors. Data Mentor acts as an AI data assistant, Aquaspec focuses on water treatment optimization, and PermitPro streamlines environmental permitting processes. By leveraging agentic AI, Delta Bravo aims to enhance operational efficiency, ensure regulatory adherence, and accelerate America's reindustrialization through intelligent automation of complex, regulated workflows. The company's solutions are trusted by industries requiring robust and auditable AI applications.

GOTURN is an open-source C++ implementation of a deep learning-based object tracker, designed for high-speed performance at 100 frames per second. It addresses the problem of single target tracking, where a bounding box label of an object in the first frame is used to track that object throughout a video. The system is robust to viewpoint changes, lighting changes, and deformations, though it does not handle occlusions. It leverages neural networks trained on generic objects, allowing it to track novel objects without fine-tuning. The repository includes installation instructions, a pretrained model, scripts for visualizing and evaluating tracking performance, and guidance for training the tracker using ALOV and ImageNet datasets. It is ideal for developers and researchers in computer vision.

Rasa-demo features Sara, a contextual AI assistant designed to demonstrate the capabilities of the open-source Rasa framework. Sara helps developers understand the Rasa framework, get started with its tools, and answers frequently asked questions. It can also direct technical questions to specific documentation, subscribe users to the Rasa newsletter, and request calls with the sales team. The repository provides all necessary files for installation and running the bot, including custom actions that can connect to external services like MailChimp and Google Sheets, requiring specific credentials for full functionality. This demo is ideal for those looking to explore and implement conversational AI solutions using Rasa.

Conundrum is an AI-driven platform offering advanced, closed-loop process control solutions for the metals, mining, and cement industries. It provides real-time, dynamic control that adapts instantly to changes, optimizing plant operations 24/7. Key features include Intelligent APC and MPC for maximized throughput and energy savings, plant-wide optimizers, physics-informed and ML models, and robust data quality management. The platform supports seamless deployment with both on-premise and cloud installation options, ensuring data security and control. Conundrum's solutions have been proven to increase EBITDA and improve operational efficiency across various processes like crushing, grinding, and flotation, contributing to both performance and sustainability.

gpt-crawler is an open-source tool designed to simplify the creation of custom GPTs by generating knowledge files from website content. Users can crawl single or multiple URLs, extracting relevant information to train their AI models. The tool offers flexible configuration options, allowing users to define the starting URL, match patterns for links, specify content selectors, and set limits on pages to crawl. It supports local execution, containerized deployment with Docker, and can also be run as an API server. The generated output, typically a JSON file, can then be uploaded to OpenAI to create custom assistants or GPTs, making it an efficient solution for developers and content creators looking to leverage their existing web content for AI applications.