Coding & Development

BAML is an open-source AI framework designed to add engineering rigor to prompt engineering, transforming it into schema engineering. This approach allows developers to build reliable AI workflows and agents by focusing on the structured models of their prompts, leading to more consistent and predictable outputs. BAML supports multiple languages including Python, TypeScript, Ruby, and Go, and is compatible with various LLM providers like OpenAI, Anthropic, Gemini, and more. It offers features like full type-safety, streaming, retries, and wide model support, even for models without native tool-calling APIs, through its SAP (schema-aligned parsing) algorithm. The framework includes native tooling for VS Code and JetBrains IDEs, providing visual prompt testing and parallel execution for faster iteration. BAML is 100% open-source and private, ensuring no data is used for training or stored beyond explicit model calls.

Nesty is an AI-powered property management system designed to help users launch and manage their rental businesses quickly and efficiently. It enables the creation of white-label property management websites without coding, offering features such as unlimited property listings with photos and availability calendars. The platform integrates with Stripe for instant payment processing and supports custom domains or free subdomains. Users can customize their website's appearance with themes, colors, and fonts. Nesty also includes an analytics dashboard for tracking bookings and revenue, and an AI assistant to help with writing property descriptions and responding to guests. It offers transparent pricing with self-serve onboarding and no setup fees or commissions.

GovLink offers an API specifically designed for verifying business registrations throughout the United States. This tool is crucial for businesses and developers who need to ensure Know Your Business (KYB) compliance and streamline due diligence processes. By integrating GovLink's API, users can automate the verification of business entities, reducing manual effort and improving accuracy. The platform also supports integration with AI agents, enhancing its utility for automated compliance workflows. Additionally, GovLink provides a free AI governance assessment tailored for UK law firms, delivering a RAG-rated report across seven key domains, demonstrating its commitment to regulatory adherence and advanced AI application.

Normally is an AI application development company focused on leveraging data and artificial intelligence to create transformative digital products and services. They specialize in building solutions that generate new value and significantly enhance operational efficiency for their clients. Their expertise lies at the intersection of human-centered design and AI engineering, allowing them to deliver bespoke AI-enabled products. Notable projects include accelerating response times for PanasonicWELL's concierge business, using AI for knowledge sharing within the NHS, and developing new services and revenue streams for IKEA by unlocking untapped household data. Normally emphasizes a mindful application of AI to achieve impactful results.

Promptly is a no-code platform designed for enterprises to build custom generative AI applications, agents, and chatbots. Users can seamlessly integrate their own data from various sources like website URLs, sitemaps, PDFs, Google Drive, and Notion exports, and connect them with major LLM models such as OpenAI, Cohere, and Stability AI. The platform offers templates for quick app building, supports model chaining, and provides embeddable widgets for websites. Promptly also facilitates collaborative app development with granular permission models and offers APIs for running apps and managing data programmatically, making it suitable for scaling AI capabilities within existing applications.

Windsurf, previously known as Codeium, is an advanced AI coding assistant designed to boost developer productivity and enterprise output. It features the Windsurf Editor, an AI-native integrated development environment, and introduces Devin, an autonomous cloud agent for delegating complex tasks. The platform also includes Cascade for local agent sessions and an Agent Command Center for managing all agents. Windsurf supports enhanced AI workflows by connecting custom tools and services, offering integrations with popular platforms like Figma, Slack, and Stripe. It aims to reduce boilerplate code and menial tasks, allowing developers to focus on creative aspects of building.

Flock is a workflow-based low-code platform designed for the rapid development of chatbots, Retrieval Augmented Generation (RAG) applications, and the orchestration of multi-agent teams. Built upon robust technologies like LangGraph, Langchain, FastAPI, and NextJS, it offers a flexible solution for creating collaborative AI systems. The platform supports various node types including Input, LLM, Retrieval, Tool, Intent Recognition, and Answer nodes, allowing for complex workflow design. Key features include persistent conversations, real-time observability with LangSmith, tool calling capabilities, and human-in-the-loop functionality for review and approval. Flock also supports open-source LLM models and multi-tenancy, making it suitable for diverse application scenarios.

Arize AI is a comprehensive AI engineering platform designed for the full lifecycle of AI applications, from development to production. It offers unified LLM observability and agent evaluation capabilities, enabling teams to build, evaluate, and improve AI agents effectively. The platform includes tools for prompt optimization, replay and debugging in a playground, prompt serving and management, and evaluation-driven CI/CD experiments. Arize AI also features LLM-as-a-Judge for automated evaluation, human annotation and queuing for data management, and open-standard tracing for observability. It helps pinpoint model failures, detect drift, analyze data patterns, and monitor embeddings to ensure high-performing and reliable AI systems.

Feedback Intelligence is an enterprise workspace designed for AI product managers and developers. It aims to personalize Large Language Models (LLMs) based on user needs by helping to gain user signals and optimize LLMs through real-world usage. The platform emphasizes the importance of feedback loops and AI user observability, ensuring that AI systems are grounded in actual usage data. This approach allows for continuous improvement and better alignment of AI products with user expectations and behaviors, ultimately accelerating Active Intelligence initiatives.

Elev8 offers modular AI platforms designed to integrate seamlessly across an organization, from the warehouse floor to the boardroom. Their solutions focus on smarter automation and delivering real results without hype. Key offerings include L1NKS Data Fabric and API Interchange for ensuring data fidelity, R3VOCAL AI Agents for revolutionizing information management and user engagement, and PULS3 for monitoring application experience from an end-user perspective. Additionally, Elev8 provides CAAS (Custom and Automated Software) for needs outside the AI scope. They serve various industries such as Banking & Finance, Satellite & Telecoms, Healthcare & Hospitality, and Retail & Construction, emphasizing speed, scale, and real-world reliability.

LLMFlows is a Python framework designed for building simple, explicit, and transparent Large Language Model (LLM) applications. It offers a minimalistic set of abstractions for utilizing LLMs and vector stores, allowing developers to construct well-structured applications like chatbots, question-answering systems, and AI agents. A core philosophy of LLMFlows is to ensure complete transparency for each component, making monitoring, maintenance, and debugging straightforward. The framework provides classes for LLMs (like OpenAI's APIs), PromptTemplates for dynamic prompt generation, and MessageHistory for managing chat conversations. For complex applications, it introduces Flow and FlowStep classes to manage dependencies between LLM calls, with AsyncFlowStep available for parallel execution to optimize performance. LLMFlows also supports integrations with vector databases like Pinecone and offers callbacks for enhanced customization and tracing.

GPTAgent is a leading no-code platform designed for building natural language AI applications quickly and efficiently. Users can create deployable AI web apps, Discord bots, and workflow automations without writing any code. The platform features an intuitive interface that allows for rapid development, enabling users to bring their AI-powered ideas to life in minutes. Key functionalities include stacking blocks to define app logic, connecting GPT-3 to the internet with a Web Search block, pulling in data with HTTP request blocks, and chaining multiple Large Language Model (LLM) blocks. Once built, apps can be published to a shareable interface or deployed as a Discord bot, making it easy to share AI prompts and functionalities with others.

SunDevs offers AI voice agents tailored for the restaurant industry, designed to automate phone orders and reservations around the clock. This solution aims to alleviate staff overload, reduce order errors, and eliminate missed calls, particularly during peak hours. The AI agents can handle complex orders, menu modifications, allergies, and special requests, integrating seamlessly with existing POS systems like PAR POS, Toast, Revel, and Qu. SunDevs emphasizes its technical excellence and deep understanding of restaurant operations, having processed millions of orders. The setup process is streamlined, promising a live agent within three weeks, allowing restaurant staff to focus on in-person hospitality.

MS-Agent is a lightweight, open-source framework designed to empower AI agents with autonomous exploration capabilities. It offers a flexible and extensible architecture, enabling developers to create agents for complex tasks such as code generation, data analysis, and general-purpose tool calling with Model Calling Protocol (MCP) support. Key features include multi-agent support, deep research capabilities for advanced exploration, and artifact-generating code generation. The framework also supports short video generation, implements the Anthropic-Agent-Skills Protocol, and provides a modern WebUI for agent interaction. Recent updates include context compression, enhanced deep research systems, knowledge search integration, and multimodal model input support, making it a versatile tool for advanced AI development.

visionplatform.ai provides a no-code platform for building and deploying AI computer vision systems quickly and effortlessly. Users can leverage ready-to-use models for tasks like people and vehicle detection, fire and smoke detection, and license plate recognition. The platform supports refining models to specific site conditions, integrating with existing systems, and maintaining ownership of data. It features a modular architecture, including detection training, business logic for operational context (OCR, dwell time), GenAI Vision Language Models (VLM) for forensic search, and Control Room AI Agents for automated responses and operator guidance. It's designed for various industries, offering solutions for safety, security, and operational efficiency.

OpenVINO™ Model Server (OVMS) is a high-performance inference server implemented in C++ for scalability and optimized for deployment on Intel architectures. It hosts models and makes them accessible to software components over standard network protocols, supporting both gRPC and REST API. OVMS offers advantages like remote inference for lightweight clients, independence from model framework and hardware, and efficient resource utilization with horizontal and vertical inference scaling. It supports generative APIs like OpenAI and Cohere, KServe, and TensorFlow Serving, and can pull models from local storage, object storage services, or HuggingFace Hub. Key features include speech generation/recognition, AI agents, image generation, text embeddings, reranking, and dynamic model inputs.

n8n-install is an open-source, self-hosted AI automation platform that simplifies the deployment of a comprehensive suite of AI and automation tools. With a single command, users can set up n8n for workflow automation, Ollama for local LLMs, Flowise for AI agents, and other powerful tools like Qdrant, Weaviate, and Supabase. The platform comes pre-configured with Caddy reverse proxy for automatic HTTPS and includes a monitoring stack with Grafana and Prometheus. It offers a private AI homelab experience, allowing users to run LLMs locally and maintain full control over their data. The installer also provides an optional import of over 300 community workflows, covering diverse use cases from AI agents to social media automations, making it a robust and scalable solution for building custom AI applications and automating repetitive tasks.

Redshred is an AI-powered document intelligence platform specifically designed to transform complex technical documentation, including maintenance manuals, schematics, and 3D technical data, into structured and searchable databases. It leverages advanced AI/ML to extract intelligence rather than just text, offering multimodal processing and knowledge graph creation to cross-reference and link information across vast document repositories with over 98% accuracy. The platform is built for enterprise-grade document intelligence, serving defense organizations and commercial teams in aerospace, maritime, cybersecurity, and industrial sectors. It supports critical operations like field service, AR/VR training, digital twins, and supply chain intelligence, ensuring data is AI-ready for LLMs without hallucinations.

Rabbitt AI is a comprehensive platform designed to empower enterprises in developing and deploying reliable Generative AI solutions. The platform specializes in leveraging enterprise data to create custom Large Language Models (LLMs) and offers a suite of services including interactive data annotation, smart labeling, and AI-assisted quality checks. Rabbitt AI provides consultation throughout the LLM adoption journey, from problem definition and data development to model building and application deployment. It emphasizes data ownership and offers a no-code solution for creating custom labeling projects, making advanced AI accessible for various business needs.

K8sGPT is an AI-powered tool designed to simplify the diagnosis and resolution of Kubernetes issues. It leverages artificial intelligence to provide intelligent insights and automated troubleshooting, making complex Kubernetes environments more manageable. The tool aims to empower users by giving them "Kubernetes Superpowers," enabling them to quickly identify and address problems within their clusters. By incorporating SRE (Site Reliability Engineering) experience into its analyzers, K8sGPT helps users understand and triage issues using simple English, streamlining the operational workflow for Kubernetes deployments.

Neural Network Compression Framework (NNCF) is a powerful tool designed to enhance OpenVINO inference by optimizing neural networks. It offers a comprehensive suite of post-training and training-time algorithms, including quantization, weights compression, and pruning, all aimed at minimizing accuracy drop while improving performance. NNCF supports models from PyTorch, TorchFX, ONNX, and OpenVINO, making it versatile for various deep learning workflows. The framework is organized as a standalone Python package and includes GPU-accelerated layers for faster compressed model fine-tuning and distributed training support. It also provides extensive documentation, tutorials, and samples to facilitate quick integration and usage.

NPCx offers revolutionary AI technology designed to create realistic digital content, specifically focusing on non-player characters (NPCs) for gaming and entertainment. The tool leverages advanced motion capture and behavior analysis to develop NPCs that exhibit more human-like actions and responses, significantly enhancing the immersive quality of interactive experiences. By providing developers with the means to craft sophisticated AI-driven characters, NPCx aims to deliver richer and more satisfying gameplay. This technology is applicable across various digital entertainment platforms, including traditional video games, augmented reality (AR), and virtual reality (VR) environments.

Navier AI is an Agent-Driven Engineering platform designed to streamline and scale simulation workflows. It offers custom engineering agents capable of handling various tasks within CAD, CFD, meshing, and general simulation processes. The platform is available as both a cloud-native solution and a local application, providing flexibility for different operational needs. Navier AI automates complex engineering steps, including flight code generation, mission planning, and FEA/FVM simulations, which significantly accelerates design exploration and development cycles. By leveraging AI, it aims to reduce manual effort and improve efficiency in engineering design and analysis.

Firecrawl is an API-first platform designed to help AI systems search, scrape, and interact with the live web. It provides clean, LLM-ready data by handling complex web scraping challenges like JavaScript rendering, dynamic content, and smart waiting. The tool offers core capabilities including searching the web for relevant content, scraping websites into various formats like Markdown and JSON, and interacting with pages through AI prompts or code to click, navigate, and operate. Firecrawl is built for performance, offering fast and reliable web data infrastructure, and is open source, fostering community contributions. It integrates seamlessly with AI agents and MCP clients, making it an essential tool for developers building AI-powered solutions that require real-time web data.