AI Agents & Automation

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.

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.

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.

Theoriq is at the forefront of the agentic economy, providing a decentralized protocol for AI agent swarms to collaborate seamlessly within DeFi ecosystems. It offers premium AI tools designed for asset management, including AlphaVault, a dynamic native ETH yield vault-of-vaults that handles allocation, monitoring, and rebalancing onchain. Additionally, the Theoriq Gold Vault provides proven DeFi yield strategies on gold collateral, compounding in gold terms. The platform also features AlphaSwarm, an AI agent swarm for answering questions about Theoriq. Its native token, THQ, incentivizes participation, offers staking rewards, and provides token-gated access to future products, aligning value accrual with protocol growth.

Eno is Capital One's digital assistant designed to enhance financial security and provide spending insights for its customers. It helps protect credit card accounts by monitoring for unusual charges and offers virtual card numbers for safer online transactions. Eno also tracks spending, identifying free trials, recurring charges, and other spending patterns to provide useful insights. Customers can interact with Eno 24/7 via text messages, the Capital One Mobile app, or online banking to check balances and ask account-related questions. Notifications are sent for important account activity, ensuring users are always informed. Eno is available across multiple platforms including mobile apps, desktop browsers, text messages, email, and smartwatches, making it a comprehensive financial assistant for Capital One users.

Rabbi AI, also known as Rabbi Ari, is an AI-powered tool designed to provide guidance and inspiration based on Torah, Talmud, and classical Jewish sources. It offers instant answers on halakha (Jewish law), ethics, holidays, and daily practice. Users can ask questions about Torah study, Jewish philosophy, and practical applications of Jewish teachings. The responses are grounded in traditional sources and adapted to Rabbi Ari's unique perspective. This tool is free to use and requires no signup, making it accessible for anyone interested in exploring Jewish texts and traditions.

PointLLM is a multi-modal large language model designed to understand colored point clouds of objects. It excels at perceiving object types, geometric structures, and appearance, effectively bypassing common issues like ambiguous depth, occlusion, or viewpoint dependency. The tool leverages a novel dataset comprising 660K simple and 70K complex point-text instruction pairs, enabling a robust two-stage training strategy. PointLLM also establishes two benchmarks, Generative 3D Object Classification and 3D Object Captioning, for rigorous evaluation. It offers capabilities for inferencing, chatting with 3D models, and evaluation using traditional metrics or GPT-4, making it a powerful resource for advanced 3D data analysis and robotics applications.

Porcupine is a highly-accurate and lightweight wake word engine developed by Picovoice, designed to enable always-listening voice-enabled applications. It utilizes deep neural networks trained in real-world environments, making it compact and computationally-efficient, ideal for IoT devices. The engine boasts broad cross-platform compatibility, supporting Arm Cortex-M, STM32, Arduino, Raspberry Pi, Android, iOS, Chrome, Safari, Firefox, Edge, Linux, macOS, and Windows. A key feature is its scalability, allowing detection of multiple always-listening voice commands without increasing runtime footprint. Developers can also train custom wake word models using the Picovoice Console, offering self-service customization. Porcupine is suitable for detecting static voice commands, providing a robust solution for hands-free control and voice interface design.

rag-tutorial-v2 is an open-source tutorial designed to guide users through the process of building Retrieval Augmented Generation (RAG) systems. This improved version (v2) focuses on practical implementation, incorporating local LLMs for enhanced privacy and control, and demonstrating effective database update strategies. The tutorial also emphasizes robust testing methodologies to ensure the reliability and performance of the RAG system. It's a valuable resource for developers and researchers looking to understand and implement advanced RAG techniques, offering a hands-on approach to integrating LLMs with external knowledge bases.

PromptBench is a PyTorch-based Python package designed as a unified evaluation framework for large language models (LLMs). It offers user-friendly APIs for researchers and developers to conduct comprehensive evaluations of LLMs, including quick performance assessments, prompt engineering method testing (like Chain-of-Thought, Emotion Prompt, and Expert Prompting), and adversarial prompt robustness analysis. The framework integrates dynamic evaluation techniques such as DyVal to mitigate test data contamination and efficient multi-prompt evaluation with PromptEval. It supports a wide range of language and multi-modal datasets and models, both open-source and proprietary, making it a versatile tool for understanding and benchmarking LLM capabilities.

Metaforms is an AI platform designed to revolutionize market research operations for agencies. It addresses common bottlenecks like lengthy survey programming, manual data validation, and slow RFP processing by leveraging AI across various workflows. The platform can generate production-ready survey code from questionnaires in any format, intelligently process data by creating validation scripts, and streamline bidding management by transforming RFPs into structured quotes. Additionally, Metaforms assists with sample management, coordinating vendors and tracking quotas in real-time, and enables large-scale AI-moderated voice interviews. It integrates with existing tools and is built for enterprise-grade security, including SOC 2 Type II Certification and GDPR compliance, without training on customer data.

SmutGPT is an uncensored AI writing assistant specifically designed for creators of erotic and NSFW content. It allows users to write freely about any topic, theme, or genre without content restrictions or filters, unlike other AI tools. The platform provides advanced writing assistance for character development, plot structuring, dialogue, and detailed scene writing for adult fiction. Users can generate unique story ideas, plot twists, and creative scenarios, receiving instant and detailed responses. SmutGPT supports multiple perspectives and narrative techniques across various genres, from romance to fantasy, and ensures user privacy by not using content to train its models. It offers both free and paid tiers with varying token limits.

StableDiffusionReconstruction is a research-oriented tool designed for reconstructing visual experiences directly from human brain activity. Utilizing Stable Diffusion models, it allows for the generation of high-resolution images based on neural data. The project, stemming from research by Takagi and Nishimoto presented at CVPR 2023, also incorporates advanced decoding techniques. These include methods for decoding text prompts from brain activity, integrating GANs for improved image quality, and incorporating decoded depth information, significantly enhancing reconstruction accuracy. This repository provides the necessary code and instructions for reproducing these methods, making it a valuable resource for researchers in neuroscience and AI.

ruby-fann is a Ruby Gem designed to interface with the FANN (Fast Artificial Neural Network) library, allowing Ruby and Rails developers to integrate neural network capabilities into their applications. This open-source library supports the implementation of both fully-connected and sparsely-connected artificial neural networks. It is lauded for its ease of use, versatility, and speed, with most of the heavy lifting performed natively. The gem provides functionalities for training neural networks with custom data, saving and loading trained networks, and implementing custom training procedures via callback methods, making it a robust solution for AI application development in Ruby environments.

Speech-Emotion-Recognition is an open-source project designed for identifying emotions in spoken language. It leverages various machine learning models, including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and Multilayer Perceptrons (MLP), all implemented within the Keras framework. The tool focuses on advanced feature extraction techniques, which contribute to its reported accuracy of around 80%. It supports Python and integrates with essential libraries such as scikit-learn for model training and evaluation, and librosa for audio feature processing. This makes it a valuable resource for researchers and developers working on speech analysis and emotion detection applications.

CoitHub positions itself as the primary entry point and router for decentralized intelligence and private LLM meshes. The platform aims to facilitate the connection and management of distributed AI systems, emphasizing privacy and decentralized control. While specific features are not detailed on the public-facing pages, its core offering revolves around enabling users to interact with and manage intelligent agents within a decentralized framework. This suggests a focus on secure and private AI operations, potentially catering to users who prioritize data sovereignty and distributed computing for their AI needs.

SparkNet is an open-source framework designed for building and training distributed neural networks using Apache Spark. It allows users to leverage the power of Spark for scalable AI model development, particularly beneficial for handling large datasets. The framework provides functionalities for quick cluster setup on EC2, training models like Cifar and ImageNet, and installing SparkNet on existing Spark clusters. It supports GPU acceleration with CUDA and offers pre-built JavaCPP binaries for various platforms, making it a robust solution for data scientists and machine learning engineers working with distributed computing environments.

Show-1 is an advanced open-source text-to-video generation model developed by Show Lab at the National University of Singapore. It uniquely combines pixel and latent diffusion models to create videos from textual descriptions. The tool provides access to various model weights, including a base model, an interpolation model, and super-resolution models, which can be downloaded from HuggingFace. Users can generate videos by running a Python script, with outputs saved in GIF format. Show-1 also offers a Gradio demo for local use and has been accepted to IJCV, highlighting its academic recognition. It is designed for researchers and developers interested in cutting-edge video synthesis.

SlickGPT is an AI-powered assistant designed to enhance user interaction with technology by anticipating needs and providing relevant information. The tool dynamically imports and handles promises for smooth operation, ensuring a responsive and efficient experience. It aims to significantly boost productivity by automating tasks and offering instant access to critical information. While specific features are not detailed on the provided website, its core function revolves around intelligent assistance and operational efficiency, making it suitable for users looking to optimize their daily digital interactions and information retrieval processes.

Static-to-Dynamic-LLMEval is the official GitHub repository for a paper detailing recent advances in large language model benchmarks, specifically focusing on data contamination. The project conducts an in-depth analysis of existing static-to-dynamic benchmarking methods designed to reduce data contamination risks. It examines methods that enhance static benchmarks, identifies their limitations, and highlights the critical gap in standardized criteria for evaluating dynamic benchmarks. The repository proposes optimal design principles for dynamic benchmarking and analyzes the limitations of current dynamic benchmarks, offering a comprehensive overview of advancements in data contamination research and guiding future efforts.

system-prompts-and-models-of-ai-tools is a comprehensive open-source GitHub repository that curates system prompts, internal tools, and AI models from a wide array of AI applications. This resource is invaluable for developers, researchers, and AI enthusiasts looking to understand the underlying mechanics and prompt engineering strategies of popular tools like Augment Code, Claude Code, Cursor, Devin AI, NotionAI, Perplexity, and many others. It provides a centralized location to explore how different AI systems are structured and prompted, fostering learning and innovation in the AI development community. The repository also highlights the importance of securing AI systems against prompt injection and extraction risks.

Kubeflow Trainer is a Kubernetes-native distributed AI platform designed for scalable large language model (LLM) fine-tuning and training of AI models. It supports various frameworks such as PyTorch, MLX, HuggingFace, DeepSpeed, JAX, and XGBoost. The platform integrates MPI into Kubernetes, facilitating efficient multi-node, multi-GPU distributed jobs across high-performance computing (HPC) clusters. This setup ensures high-throughput communication crucial for large-scale AI training requiring rapid synchronization between GPU nodes. Kubeflow Trainer also integrates with the Cloud Native AI ecosystem, including Kueue for topology-aware scheduling and multi-cluster job dispatching, and JobSet/LeaderWorkerSet for AI workload orchestration. It features a distributed data cache for zero-copy transfer of large-scale data directly to GPU nodes, optimizing memory efficiency and GPU utilization. AI practitioners can leverage the Kubeflow Python SDK to develop and fine-tune LLMs using the Trainer APIs: TrainJob and Runtimes.

Transformer Engine (TE) is an open-source library developed by NVIDIA for significantly accelerating Transformer models on NVIDIA GPUs. It achieves this by leveraging 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada, and Blackwell GPUs, including MXFP8 and NVFP4 formats on Blackwell. This results in improved performance and reduced memory utilization during both training and inference processes. TE provides highly optimized building blocks for popular Transformer architectures and an automatic mixed precision-like API that integrates seamlessly with existing framework-specific code. It also offers a framework-agnostic C++ API for broader integration, simplifying mixed-precision training for users by internally managing scaling factors.