Coding & Development

Khorus serves as a universal communication layer for intelligent systems, specifically designed to make AI agents interoperable on-chain. It provides the fastest way to deploy A2A (Agent-to-Agent) agents, powered by ERC-8004 identity and x402 payments. The platform allows users to create agent workforces, assign tasks, and run or sync operations. A key feature is the ability to tokenize creations and list them on a marketplace or launch them through Genesis with DAO Pools. Khorus integrates with various agent APIs and data tools, routing calls through x402 for automated signals, metered usage, and trustless on-chain settlement. It supports the design and deployment of complex dApps through coordinated agent workspaces, ensuring each agent is verified on-chain and can communicate across different chains and environments.

DeepLearning.scala is an open-source library designed for building complex neural networks using Scala. It supports differentiable programming, allowing users to construct neural networks from mathematical formulas and calculate derivatives for weights. A key differentiator is its ability to create dynamic neural networks, where the structure can change during runtime based on Scala functions and control flows. This enables programmers to build sophisticated networks with familiar coding paradigms. The library also emphasizes functional programming, leveraging Monads and Applicative type classes for composable layers and parallel computations. DeepLearning.scala 2.0 is organized around Dependent Object Type calculus (DOT), providing mixin-able plugins for extending functionality, including algorithms, models, and hyperparameters, all with static type checking.

EmbedAPI serves as a comprehensive AI integration platform designed to simplify the process of connecting to various AI models. It offers a unified API that allows developers to integrate leading AI models such as OpenAI, Anthropic, and Vertex AI quickly and efficiently. The platform aims to streamline AI development by providing a single point of access, reducing the complexity typically associated with managing multiple AI service providers. This enables faster deployment of AI capabilities into applications and services, making it an essential tool for developers looking to leverage diverse AI technologies without extensive setup.

NBoost is a scalable, open-source platform designed to enhance the relevance of search results by deploying state-of-the-art transformer models. It acts as a neural proxy, sitting between a client and a search engine like Elasticsearch, to rerank results based on fine-tuned models. This allows for domain-specific neural search engines and can improve other ranked input tasks such as question answering. NBoost offers easy installation via Docker, PyPi, or Kubernetes, and provides benchmarks demonstrating significant search boost compared to traditional methods. It supports both PyTorch and TensorFlow dependencies, making it flexible for various deployment environments.

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.

search is an open-source Go library designed for embedded vector search and semantic embeddings, utilizing llama.cpp. It offers an efficient solution for projects requiring semantic power without the complexities of traditional search systems. The library supports GGUF BERT models and provides GPU acceleration for quicker computations. It's particularly well-suited for datasets with fewer than 100,000 entries, offering features like llama.cpp integration without cgo, support for various BERT models in GGUF format, and precompiled binaries with Vulkan GPU support. Users can create and save search indexes from computed embeddings, enabling basic vector-based searches in Go applications.

Text Generation Inference (TGI) is an open-source toolkit designed for deploying and serving Large Language Models (LLMs) with high performance. Developed by Hugging Face, it's used in production for services like Hugging Chat and the Inference API. TGI supports popular open-source LLMs including Llama, Falcon, and BLOOM, offering features such as tensor parallelism for faster inference on multiple GPUs, token streaming, and continuous batching for increased throughput. It also includes optimized transformers code with Flash Attention and Paged Attention, various quantization methods (bitsandbytes, GPT-Q, AWQ, Marlin, fp8), and hardware support for Nvidia, AMD, Inferentia, Intel GPU, Gaudi, and Google TPU. While TGI is now in maintenance mode, it has influenced the development of other optimized inference engines like vLLM and SGLang, which Hugging Face now recommends.

xtream specializes in developing high-quality digital products and AI solutions for businesses. Their mission is to demonstrate that quality in design and execution always yields positive returns, contrasting with the time, money, and embarrassment often caused by poor implementations. They offer tailor-made services in both AI Solutions and Digital Products, built with expertise and knowledge to ensure they become valuable assets for their clients. The company emphasizes a hands-on approach, as highlighted by their featured case study with WeRoad, where they combined UX and AI to optimize tour planning, leading to faster and better decision-making. xtream is based in Milan, Italy, and serves a range of customers, from scale-ups to large corporations.

KS Smart Solutions, incorporated in 2016, offers bleeding-edge automated solutions tailored to client needs across diverse industries. They focus on digital transformation through Industry 4.0, AI, automation, and cloud technologies. Their expertise spans VR/AR solutions, Machine Learning/AI, web/mobile app development, and enterprise solutions. KS Smart Solutions aims to help clients achieve their digital objectives by developing customized IT solutions, enhancing agility, productivity, quality, and sustainability. They serve sectors like manufacturing, smart cities, defense, education, dairy, and entertainment, providing innovative solutions from immersive VR simulations for training to integrated inventory management systems.

OpenAI-API-dotnet is an unofficial C#/.NET SDK designed for seamless integration with OpenAI's powerful APIs, including GPT-3.5/4, GPT-4-Turbo, and DALL-E 2/3. This library provides a simple .NET wrapper, enabling developers to easily incorporate advanced AI capabilities into their applications. While originally an unofficial project, Microsoft has since adopted and transitioned this library into an official C# OpenAI library, ensuring full coverage and up-to-date functionality in its v2.0.0-beta.3 and later versions. The original GitHub repository remains a valuable resource, documenting the library through version 1.11, which is still available on Nuget. It supports .NET Standard 2.0, making it compatible across various .NET versions and platforms like Windows, Linux, and Mac, for console apps, WinForms, WPF, ASP.NET, Unity, and Xamarin.

speech-to-text-nodejs is an open-source sample Node.js application designed to demonstrate the capabilities of the IBM Watson Speech to Text service. This tool leverages IBM's advanced speech recognition to convert spoken language into text across various languages. It features continuous transcription of incoming audio, delivering results to the client with minimal delay and correcting them as more speech is processed. The service is primarily accessed via a WebSocket interface, though a REST HTTP interface is also available. The application provides clear instructions for local setup and deployment to IBM Cloud, making it accessible for developers looking to integrate speech-to-text functionality into their projects.

Twilio offers a comprehensive Customer Engagement Platform (CEP) that integrates communication APIs with AI and first-party data. Developers can leverage Twilio's APIs for various communication channels including SMS, WhatsApp, voice, and email, alongside features like conversational AI, customer data platforms, and authentication tools. The platform supports use cases such as fraud prevention, alerts, marketing, and customer support, allowing businesses to create personalized customer experiences. Twilio emphasizes its builder-centric approach, providing tools and support for developers to quickly integrate and scale communication solutions, backed by transparent pricing and a free trial option.

Canopy API is a modern solution for developers and businesses needing real-time Amazon product data. It provides access to product information, pricing, reviews, sales estimates, and search results directly from Amazon.com. The API supports multiple interfaces including REST, GraphQL, MCP, and AI Skills for LLMs, allowing for flexible integration into various workflows. Key features include retrieving detailed product data like title, description, pricing, sales, and stock estimations, as well as collecting comprehensive review data for analysis. Users can also retrieve product search results to monitor rankings. The service is designed to scale with usage, offering volume discounts, and provides detailed documentation and open-source examples for quick integration.

Sendbird is an AI customer experience platform designed for enterprises, offering robust communication APIs and an AI concierge named delight.ai. The platform focuses on enhancing customer engagement and loyalty through hyper-personalized experiences across the entire customer journey. It provides a comprehensive suite of communication solutions, including chat APIs, voice and video call APIs, and an AI agent platform. Key features include advanced messaging capabilities, moderation tools, analytics, and integrations with systems like Salesforce. Sendbird is built on a trusted communication infrastructure, powering billions of conversations monthly, and ensures security and compliance with standards like SOC 2, ISO27001, GDPR, and HIPAA.

Luxand.cloud offers a powerful, cloud-based Face Recognition API designed for seamless integration into web and mobile applications. It provides advanced capabilities for face search, matching, and recognition, enabling developers to accurately identify individuals and analyze facial attributes like age, gender, and emotions. The API is built for high performance, processing thousands of facial images in seconds with impressive accuracy and stability. Luxand.cloud also offers specialized APIs like Baby Maker for generating future baby images and Aging API for applying realistic aging effects. With a focus on security, it stores only neural network templates, not photos, ensuring data privacy. It supports various programming languages and offers a cost-effective, scalable solution for diverse industries.

qdrant-client is a Python client library designed for seamless interaction with the Qdrant vector search engine. It offers comprehensive type definitions for all Qdrant API methods, facilitating both synchronous and asynchronous requests. The library supports a local mode for development, prototyping, and testing without requiring a running Qdrant server, and can easily switch to server mode for scaling. Key features include REST and gRPC support, minimal dependencies, and extensive test coverage. Additionally, it provides an Inference API for creating embeddings locally with FastEmbed or remotely with Qdrant Cloud models, simplifying the process of generating and uploading vectors.

Deeplearning4j is a comprehensive ecosystem designed for deploying and training deep learning models within the Java Virtual Machine (JVM) environment. It offers a high-level API for building MultiLayerNetworks and ComputationGraphs, supporting various layers including custom ones. A key feature is its ability to import models from popular frameworks like Keras, TensorFlow, ONNX, and PyTorch. The suite includes ND4J, a general-purpose linear algebra library with over 500 operations, and SameDiff, an automatic differentiation/deep learning framework similar to TensorFlow's graph mode. DataVec provides ETL capabilities for machine learning data, handling diverse formats and sources. The underlying C++ library, LibND4J, ensures high performance with CPU and GPU acceleration. Deeplearning4j supports Windows, Linux, and macOS, with broad hardware compatibility.

LeFlow is an open-source tool-flow designed to bridge the gap between TensorFlow deep neural networks and synthesizable hardware, specifically FPGAs. It achieves this by integrating Google's XLA compiler with the LegUp high-level synthesis tool, enabling the automatic generation of Verilog code from TensorFlow specifications. This facilitates the deployment of deep neural networks on FPGAs, offering a flexible approach to hardware acceleration. The tool includes a testing framework with 15 building blocks to verify installation and functionality, ensuring that generated circuits match original TensorFlow results. It also provides examples ranging from simple tests to more complex applications, making it a comprehensive solution for hardware synthesis of AI models.

TensorFlow Recommenders Addons (TFRA) is an open-source collection of projects designed to enhance TensorFlow's capabilities for building large-scale recommendation systems. It primarily introduces Dynamic Embedding Technology, which allows for trainable key-value data structures within TensorFlow, leading to better recommendation effects compared to static embedding mechanisms by avoiding hash conflicts. TFRA is compatible with native TensorFlow optimizers, initializers, CheckPoint, and SavedModel formats. It fully supports training and inference of recommender models on GPUs, including integration with TF Serving and Triton Inference Server. The project also offers support for various Key-Value implementations as dynamic embedding storage, such as cuckoohash_map and HierarchicalKV, and supports both half-synchronous and asynchronous training methods.

chatglm-openai-api is an open-source project that offers an OpenAI-compatible API for various large language models, specifically ChatGLM-6B, ChatGLM2-6B, and Chinese Embeddings Models. This tool simplifies the integration of these powerful models into existing applications by providing a standardized API interface, similar to what developers are accustomed to with OpenAI. It supports loading models from Hugging Face and running inference on GPUs, with options for local loading and multi-GPU inference. The project also includes advanced features like ngrok and Cloudflare tunnel integration for exposing the API, making it accessible for development and deployment. It's designed for developers looking to leverage these specific models with ease.

Same.dev offers an innovative approach to website development, enabling users to create websites simply by chatting with an AI. This platform aims to streamline the development process, making it accessible even for those without extensive coding knowledge. Users can interact with the AI to describe their desired website, and the tool will generate the necessary components. The platform emphasizes ease of use, allowing for rapid prototyping and development of web projects. It is designed to empower individuals and teams to bring their web ideas to life efficiently.

api-for-open-llm is an open-source project that offers a unified backend interface for a wide range of open large language models, designed to mimic the OpenAI ChatGPT API. This allows developers to seamlessly integrate and utilize models such as LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, and ChatGLM into their applications. Key features include support for streaming responses, enabling printer-like effects, and the implementation of text embedding models crucial for document knowledge Q&A. It also integrates with LangChain for advanced LLM development and supports loading fine-tuned LoRA models. The project simplifies the process of using open models as ChatGPT alternatives by requiring only simple environment variable modifications, and it offers vLLM for inference acceleration and concurrent request handling.

one-api is an open-source LLM API management and distribution system designed to streamline access to various large language models. It supports a wide range of providers including OpenAI, Azure, Anthropic Claude, Google Gemini, DeepSeek, and many others, unifying them under a single, standard OpenAI API format. This system facilitates key management, token management with expiration and IP restrictions, and secondary distribution. It offers features like load balancing across multiple channels, stream mode for real-time effects, and multi-machine deployment. Users can manage channels, user groups, and redemption codes, along with detailed quota tracking. The tool is deployable as a single executable file, offers Docker images for quick setup, and includes an English UI, making it accessible for developers looking to manage and distribute LLM APIs efficiently.

one-hub is an open-source OpenAI interface management and distribution system, forked from songquanpeng/one-api. It significantly expands upon the original by supporting a wider range of models, including Gemini, Claude, and various Chinese LLMs. The system features a redesigned UI, user dashboards, and administrator analytics for comprehensive data statistics. Key enhancements include improved function calling for non-OpenAI models, dynamic user model lists, custom speed testing models, and support for various payment methods. It also offers advanced features like model-specific rate limits (RPM), Prometheus monitoring, and Uptime Kuma status monitoring, making it a robust solution for managing and distributing access to multiple large language model APIs.