AI Agents & Automation

OpenStall is a social experiment and marketplace designed for AI agents to trade capabilities with each other. It provides a robust economic environment where agents can buy and sell services like image generation, video generation, voice & audio, social media posting, web scraping, and marketing strategy. The platform incorporates essential features for a functioning economy, including escrow protection to secure transactions until task completion, a reputation system with ratings and success rates to filter out unreliable agents, and transparent fixed pricing for each capability. Users can choose from three modes: Save Money by delegating tasks to cheaper specialist agents, Earn Credits by selling their specialized capabilities, or Extend Abilities by finding specialist agents for specific needs. The platform offers 1,000 free credits upon signup, with 1,000 credits equating to $1 USD.

micro_diffusion is an open-source repository from Sony Research that provides a minimalistic implementation for training large-scale diffusion models from scratch with an extremely low budget. Utilizing only 37 million publicly available real and synthetic images, it can train a 1.16 billion parameter sparse transformer for approximately $1,890, achieving a strong FID score on the COCO dataset. The repository includes training code, dataset code, and pre-trained model checkpoints for off-the-shelf generation. It supports progressive training from low to high resolution and incorporates patch masking for performance optimization and reduced training time.

neurojs is an open-source JavaScript framework designed for deep learning and reinforcement learning applications within the browser environment. While it mainly focuses on reinforcement learning, it is versatile enough for various neural network-based tasks. The library includes practical examples and demos, such as a 2D self-driving car visualization, to showcase its capabilities. It supports advanced features like uniform and prioritized replay buffers, advantage-learning, and models such as deep-q-networks and actor-critic (via deep-deterministic-policy-gradients). neurojs also allows for binary import and export of network configurations, including weights, and is built for high performance. However, development on neurojs is no longer actively maintained, with the recommendation to use more general frameworks like TensorFlow-JS.

Cultivation > Accumulation presents a novel approach to AI agent memory, arguing that agents suffer from a knowledge architecture problem rather than just a retrieval problem. This framework, built by WikiBonsai, proposes storing knowledge in structured plain text files using extended markdown. These files incorporate typed links, structured attributes, and an explicit semantic hierarchy to form a complete knowledge graph. This design eliminates the need for complex query layers or proprietary databases, making the knowledge base mutually intelligible to humans, LLMs, and scripts. The system supports long-term conceptual navigation, allowing agents to understand where concepts live relative to others, fostering true understanding beyond mere retrieval. It also features deterministic operations via `tendr-cli` to ensure structural integrity and prevent errors that can arise from LLM-driven generation.

Automation Intelligence provides advanced solutions for industrial automation, leveraging digital twin consulting and decision science technology. Their services include developing physics-enabled virtual models of operations to identify and resolve automation challenges, allowing for rapid concept testing, virtual commissioning of new equipment, capacity planning, and operator training in a safe environment. Additionally, they deploy mathematical algorithms to optimize systems in real-time, utilizing data to orchestrate human and automated resources for efficient labor utilization, improved on-time deliveries, optimized production planning, and increased throughput. This is particularly beneficial for eCommerce, retail, and manufacturing sectors seeking to enhance operational efficiency and reduce downtime.

Reka AI is a frontier AI research company specializing in building unified multimodal foundation models. Unlike single-modality systems, Reka’s models are designed to process and reason across text, image, video, and audio simultaneously, providing enterprise-grade intelligence for complex, real-world workflows. Key offerings include Reka Vision for multimodal perception and reasoning across video and images, Reka Research for state-of-the-art foundation models, and Reka Speech for advanced audio understanding. Reka also offers a tiered family of models like Reka Core, Reka Flash, and Reka Spark, optimized for various use cases from high-stakes reasoning to on-device computing. The platform supports flexible deployment options including cloud, VPC, and on-premise environments.

CUA - Computer Use Agent 2.0 is an AI-powered application available as a Hugging Face Space that specializes in image captioning. Users can upload images to the platform, and the tool will automatically generate detailed, descriptive captions based on the visual content of the photo. This functionality is particularly useful for tasks requiring automated image analysis and textual representation, such as content creation, accessibility enhancements, or data annotation. The tool focuses on providing clear and comprehensive descriptions, making it a valuable asset for anyone needing to quickly understand or categorize visual information.

GreyLabs AI offers human-grade Voice AI solutions specifically designed for Banking, Financial Services, and Insurance (BFSI) institutions. This platform empowers organizations to automate and enhance their contact center operations, covering critical functions such as sales, collections, and customer support. By leveraging advanced Voice AI Agents, GreyLabs AI facilitates scalable interactions, allowing businesses to manage high volumes of customer engagements efficiently. The technology is built to understand and respond with human-like quality, ensuring effective communication and improved customer experience across various touchpoints. It integrates sophisticated voice capabilities to streamline processes and drive operational efficiency within the financial sector.

KnowledgeGPT is an AI-powered platform designed for knowledge retrieval and interactive learning. Users can ask questions on any topic and receive beautifully crafted, interactive pages tailored to their curiosity, rather than just a list of links. The platform offers customizable experiences, including interactive courses for language learning, calculators for financial planning, data explorers for product comparisons, visual timelines for historical events, interactive quizzes for general knowledge, step-by-step guides for recipes, and travel guides for destination planning. It aims to transform how users discover and interact with information, making learning and data exploration more engaging and personalized.

Waabi is pioneering Physical AI, focusing on the development of autonomous driving technology, initially for trucks and expanding to robotaxis. The company utilizes a next-generation approach centered around an end-to-end interpretable and verifiable AI model. This model is powered by an industry-leading neural simulator, which significantly reduces the time and resources required to bring self-driving vehicles to public roads safely and at scale. Waabi's platform aims to unlock true scalability, generalizing across different vehicle types, geographies, and environments, and setting new standards for AV safety through a simulation-first approach and rigorous validation.

OmniAnomaly is an open-source AI tool designed for robust anomaly detection in multivariate time series. It leverages a stochastic recurrent neural network architecture, combining Gated Recurrent Unit (GRU) and Variational Autoencoder (VAE) components. The core functionality involves learning the normal patterns within complex time series data and then using reconstruction probability to identify deviations that signify anomalies. This model is particularly useful for analyzing datasets like SMAP, MSL, and SMD, which include server machine data and satellite telemetry. The tool provides a comprehensive workflow from data preprocessing to model training, anomaly scoring, and threshold determination using the POT model, making it suitable for researchers and developers working with time series anomaly detection.

OpenCV (Open Source Computer Vision Library) is a powerful and widely adopted library designed for computer vision and machine learning tasks. It offers a comprehensive suite of tools for image and video analysis, including functionalities for object detection, facial recognition, image manipulation, and 3D reconstruction. The library supports various programming languages like C++, Python, and Java, making it accessible to a broad range of developers and researchers. Its open-source nature fosters a vibrant community, contributing to continuous development and a rich ecosystem of resources, tutorials, and applications. OpenCV is a fundamental tool for anyone working on projects involving visual data interpretation and processing.

xpander.ai delivers personal AI agents designed to make every employee 10x more capable, mirroring the impact coding agents had on developers. These agents integrate with over 2,000 enterprise tools, including Salesforce, Jira, SAP, and Slack, and can be deployed in minutes with no per-user setup or training required. The platform emphasizes governance and auditability, running entirely in your VPC or on-prem with SOC 2 Type II certification. Agents are always-on, container-based, and feature infinite memory, allowing for proactive alerts, scheduled tasks, and persistent context across sessions. xpander.ai supports various roles, from sales and engineering to operations and HR, adapting automatically to each person's needs and enabling real actions like creating tickets, sending emails, and updating records.

Playgent offers specialized reinforcement learning (RL) environments tailored for the finance and banking sectors. These environments simulate realistic market conditions, document processing workflows, and complex decision-making scenarios, mirroring real-world trading, compliance, and operational tasks. The platform provides challenging financial tasks, verification rubrics, and production-ready environments for post-training AI agents. Playgent emphasizes that the quality of the environment directly impacts the quality of the agent, and their expert-curated tasks are benchmarked to ensure high performance. Examples include environments for LBO returns analysis, earnings normalization, and M&A synergy analysis, all designed to help agents excel at financial decision-making.

Parlant is an open-source interaction control harness designed for customer-facing AI agents, optimizing for controlled, consistent, and predictable customer interactions with Large Language Models (LLMs). It streamlines the development and maintenance of enterprise-grade B2C and sensitive B2B interactions, ensuring they are compliant and on-brand. Parlant addresses the challenges of conversational context engineering by providing an agentic harness that optimizes context engineering for conversational use cases. It allows developers to define rules, knowledge, and tools once, with the engine dynamically narrowing the context in real-time to what's immediately relevant for each turn of the conversation. This approach ensures maximum control over conversation experience, prevents unwanted behaviors by applying constraints, and offers a rapid feedback loop for product adjustments.

InProfiler is an AI-powered tool designed to optimize LinkedIn networking and lead profiling. It intelligently analyzes and categorizes incoming LinkedIn connection requests, helping users identify and prioritize high-potential leads that align with their professional objectives. By streamlining this process, InProfiler enables users to focus their efforts on the most valuable connections, enhancing their lead management and outreach strategies. The tool aims to integrate with CRM systems, providing a comprehensive solution for professionals looking to leverage LinkedIn for business growth and networking efficiency. It's particularly useful for those who receive a high volume of connection requests and need an automated way to sort and evaluate them.

Docketry.ai offers an Agentic AI Platform designed for modern enterprises to transform documents into decisions, enabling faster, safer, and smarter operations. The platform provides pre-built agentic teams for various functions like FinOps, ITOps, HROps, Fraud Management, and Policy Acceptance, which can be deployed within weeks. Key products include ExtractIQ for document intelligence, NeuroDesk for cognitive intelligence, OpsIQ for operations intelligence, and CASIE for conversational intelligence. Docketry.ai aims to deliver significant efficiency gains (up to 20X), cost savings (up to 75%), and accuracy (up to 95%), helping businesses achieve AI maturity across different stages from efficiency to autonomy. It caters to industries such as insurance, financial services, banking, and supply chain.

Shift Opus offers a comprehensive suite of AI-driven solutions designed to simplify success in the digital world. Their services include AI-driven automation to reclaim time by automating tedious tasks, seamless systems and tools automation for efficient connectivity between existing systems, and a Business Analyst as a Service for insightful strategy and process optimization. The platform emphasizes tailored excellence, innovation with the latest AI technology, and building strong partnerships. Shift Opus follows a rigorous methodology involving in-depth research, customized strategy development, hands-on implementation and support, and continuous learning to ensure evolving solutions for businesses.

Towhee Examples offers a diverse collection of applications designed to analyze unstructured data using the Towhee framework. These examples cover a wide range of tasks, such as reverse image search, reverse video search, audio classification, and question and answer systems. Additionally, it includes applications for molecular search and deepfake detection. The platform aims to democratize the process of generating embedding vectors (x2vec) by providing easily runnable examples that leverage machine learning models and operations. It supports various models like ResNet, VGG, EfficientNet, ViT for image tasks, DPR for NLP, and Pytorchvideo for video. This resource is ideal for developers and data scientists looking to implement advanced data analysis solutions.

Curebase is an AI-native eClinical platform designed to unify sponsors and sites on a single system, accelerating clinical trials from study startup to database lock. It provides a comprehensive suite of tools including ePRO/eCOA for patient-reported outcomes, eConsent for electronic informed consent, Electronic Data Capture (EDC), and robust patient recruitment capabilities. The platform also features dedicated site software (Sitebase) to streamline patient management and automate workflows for research sites. Curebase aims to improve data quality and boost participant engagement, adapting to the needs of biotech, MedTech, pharma, and CROs, making it suitable for lean teams and global programs alike.

The I-NERGY Project is an EU-funded initiative dedicated to advancing Artificial Intelligence for Next Generation Energy. Its core vision is to strengthen the AI-on-demand platform's service layer, fostering the development of new AI-based energy services. The project aims to reshape the energy value chain by enhancing business processes and promoting environmental sustainability. With 17 partners across 9 countries and 9 pilot hubs, I-NERGY facilitates innovation through various events, open calls, and collaborations within the ICT-49 project cluster. It provides a framework for integrating AI into the energy sector, supporting research, development, and the adoption of advanced technologies.

notebooklm-mcp is a server designed to bridge the gap between AI agents like Claude Code, Codex, and Cursor, and Google's NotebookLM. It allows these agents to directly query NotebookLM for information, ensuring zero-hallucination answers grounded in your own documentation. The tool addresses common problems with traditional AI research, such as massive token consumption, inaccurate retrieval, and hallucinations, by leveraging NotebookLM's pre-processed knowledge base. It supports persistent authentication, library management with tags and descriptions, and cross-client sharing, enabling deep, iterative research where agents automatically ask follow-up questions to build complete understanding before generating code or responses. This eliminates the need for manual copy-pasting and significantly improves the accuracy and efficiency of AI-driven research.

Midship's AI autonomously performs SOX testing and beyond, offering a solution to automate over 85% of SOX controls. The platform's AI agents, built on IIA standards, follow your audit plan, perform tests, and generate fully documented work papers. This allows auditors to focus on high-judgment tasks, significantly cutting co-sourcing costs while maintaining audit quality. Midship supports a wide range of controls, from ITGC to manual financial reviews, and is compatible with Excel through its add-in for seamless work paper review. The tool is SOC 2 Type 2 compliant, ensuring high standards for data security, confidentiality, and integrity, and offers flexible data storage options.

onnx-go offers Go developers the capability to integrate pre-trained neural networks into their applications. It acts as an interface to the Open Neural Network Exchange (ONNX) format, enabling the decoding of ONNX binary models into a computation backend. This tool is particularly useful for adding machine learning capabilities to Go code without requiring specialized data science skills or being tied to a specific framework. While the implementation of the ONNX spec is partial for import and non-existent for export, it supports various backends like Gorgonia. The project is actively maintained by Orama and provides utilities to run models from the ONNX model zoo, making it a valuable resource for Go-based AI development.