AI Agents & Automation

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.

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.

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.

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.

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.

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.

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.

TreeQuest is an open-source Python library designed for advanced tree search algorithms, particularly useful for scaling Large Language Model (LLM) inference. It offers a flexible API that allows for customizable node generation and scoring logic, making it adaptable to various applications. The library implements AB-MCTS-A (ABMCTS with Node Aggregation) and AB-MCTS-M (ABMCTS with Mixed Models) algorithms, as well as Multi-LLM AB-MCTS support. Key features include checkpointing and resuming searches, an ask-tell interface for batched sampling, and visualization utilities to render search trees. TreeQuest is ideal for developers and researchers working on optimizing LLM performance and exploring complex decision-making processes.

text-generation-webui-colab offers a convenient Gradio web user interface for deploying and interacting with Large Language Models (LLMs) directly within a Google Colab environment. This open-source project supports a wide range of LLMs, including popular models like Llama 2, Vicuna, Falcon, and Mistral, often with GPTQ 4-bit quantization for efficient use. It's particularly useful for researchers, developers, and enthusiasts who want to experiment with different LLMs without extensive local setup. The repository provides numerous Colab notebooks pre-configured for specific models, simplifying the process of getting started with text generation, instruction following, and other LLM-based tasks.

TimeSeries_Seq2Seq is a GitHub repository offering a valuable collection of notebooks and code designed to facilitate the understanding and implementation of sequence-to-sequence (seq2seq) neural networks specifically for time series forecasting. The networks within this repository are built using popular deep learning frameworks, Keras and TensorFlow. It serves as a practical resource for data scientists and researchers looking to apply advanced neural network architectures to predict future values based on historical time-dependent data. The repository includes instructions for setting up the environment and working with the provided notebooks, making it accessible for those interested in hands-on learning and application of seq2seq models in time series analysis.

x-cmd is a comprehensive toolkit designed to empower AI agents and streamline command-line operations across various POSIX shells like bash, zsh, and ash. It features a Shell Standard Library with over 300 modules written in shell/awk, bringing modern capabilities to even minimal environments like BusyBox or Alpine. Beyond its core modules, x-cmd includes an On-Demand Package System, `pkg`, which provides access to over 600 curated modern CLI tools such as `jq`, `fzf`, and `ripgrep`, ensuring environment compatibility and minimizing dependencies. The tool is optimized for AI agents, allowing access to major AI providers like OpenAI, Gemini, and DeepSeek directly from the shell with a pure-shell agent under 2MB. Its design prioritizes flexibility, native system integration, and tool-chaining, making it ideal for scenarios where network latency and LLM throughput are critical.

XuanCe (玄策) is an open-source, comprehensive, and unified deep reinforcement learning (DRL) library designed to provide high-quality and easy-to-understand implementations of DRL algorithms. It aims to address the sensitivity of DRL algorithms to hyper-parameter tuning and unstable training processes by offering a robust and flexible framework. XuanCe is highly modularized, easy to install and use, and supports flexible model combinations. It includes abundant algorithms for various tasks, supporting both DRL and Multi-Agent Reinforcement Learning (MARL) tasks. The library boasts high compatibility across different deep learning backends (PyTorch, TensorFlow2, MindSpore), operating systems (Linux, Windows, MacOS), and hardware (CPU, GPU). Key features include fast running speed with parallel environments, distributed training with multi-GPUs, automatic hyperparameter tuning, and good visualization effects with TensorBoard or Weights & Biases.

Weighted-Boxes-Fusion is a comprehensive Python library designed for advanced object detection tasks, specifically focusing on ensembling bounding boxes from multiple models. It offers implementations of several key methods, including Non-maximum Suppression (NMS), Soft-NMS, Non-maximum weighted (NMW), and its namesake, Weighted Boxes Fusion (WBF). The WBF method is highlighted for providing superior results compared to other ensembling techniques. The library supports various dimensions, with specific functions for 3D boxes and 1D line segments, the latter being particularly useful for Natural Language Processing (NLP) tasks like Named-entity recognition (NER). It is built with Python 3.*, Numpy, and Numba, ensuring efficient processing. Usage examples are provided for both multiple and single model predictions, making it accessible for developers looking to enhance their object detection pipelines.

Codic Solution is a privately owned software services company specializing in custom software development and AI integration for businesses worldwide. They offer a range of services including system design, SaaS development, AI integration, and data science. Their expertise covers areas like enterprise resource planning (ERP), customer relationship management (CRM) integration, cloud-based solutions, mobile app development, and web application development. Codic Solution focuses on delivering scalable, secure, and intuitive solutions to enhance operational efficiency, automate workflows, and drive digital transformation for their clients.

Emergence AI delivers mission-critical agentic infrastructure for enterprises, specializing in verified and governed AI agents. These agents are designed to plan, reason, and act across complex systems, from semiconductor design to broader enterprise operations. The platform offers solutions built on determinism, ensuring predictable and verifiable operations; governed everywhere, with formally verified and risk-managed agent networks; and continual self-improvement through persistent memory systems. Emergence AI's solutions include Emergence Agents, Emergence Assistant, and Semantic Intelligence, with a strong focus on the semiconductor industry for design, verification, and silicon lifecycle automation. Their expertise in context management and long-term memory sets a new standard for AI memory performance.

Youtu-GraphRAG is a revolutionary framework designed for graph retrieval-augmented complex reasoning, offering a vertically unified agentic paradigm. It jointly connects the entire framework as an intricate integration based on graph schema, allowing seamless domain transfer with minimal intervention. The tool boasts a 33.6% lower token cost and 16.62% higher accuracy over state-of-the-art baselines, making it ideal for multi-hop reasoning, summarization, and knowledge-intensive tasks. Key innovations include schema-guided hierarchical knowledge tree construction, dually-perceived community detection, and agentic retrieval with iterative reflection. It also provides advanced construction and reasoning capabilities for real-world deployment, including user-friendly visualization and parallel sub-question processing.

ZeAI Soft is a cutting-edge product and service-based company focused on AI, Machine Learning, and Web App Development. They aim to empower businesses with smart, scalable technology, supported by partnerships with global tech leaders. The company emphasizes a customer-centric approach, working closely with clients to understand unique challenges and provide customized solutions. ZeAI Soft offers end-to-end service, handling projects from concept to execution with precision, and provides continuous support and maintenance post-delivery. They differentiate themselves through a strong emphasis on continuous improvement and innovation, ensuring their technology stays current with industry trends.

Synnada is an AI infrastructure company dedicated to rethinking how intelligent systems are built. It provides the foundational technology for data science and content understanding, enabling the creation of reliable, scalable, and agent-native systems. Built by Apache DataFusion contributors, Synnada's offerings include Mithril for efficient model compilation, Tenet for multi-cloud AI workload deployment, and Agentia, a runtime for persistent agent systems with first-class code execution. This infrastructure supports the agentic economy, allowing intelligent agents to operate continuously across clouds, datasets, and decision loops, ensuring correctness, efficiency, and long-term operability for production-grade AI.

Bridgesoft is an agricultural technology firm that integrates deep learning, image processing, embedded hardware, and edge computing into existing farming machinery. The company's primary goal is to provide high-tech solutions for efficiency and savings in pesticide and liquid fertilizer application, aiming for up to 90% reduction in chemical use. Bridgesoft's technology helps farmers reduce costs, increase profitability, and compete globally by bridging the gap between agricultural practices and advanced technology. The company develops 100% local software, AI models, and electronic hardware through its R&D team, focusing on making agricultural technology accessible to all farmers, including small-scale operations, and promoting environmentally friendly and sustainable farming practices.