Coding & Development

vocode-core is an open-source Python library designed to simplify the creation of voice-based LLM applications. It facilitates real-time streaming conversations with large language models, allowing developers to deploy these agents to phone calls, Zoom meetings, or integrate them into personal assistants. The library provides easy abstractions and integrations for transcription services (e.g., AssemblyAI, Deepgram), LLMs (e.g., OpenAI, Anthropic), and synthesis services (e.g., Rime.ai, Eleven Labs). Its modular nature supports building custom voice agents and offers quickstart guides for various use cases, including spinning up conversations with system audio and managing outbound phone calls.

Jeen.ai provides a seamless AI foundation designed for enterprise environments, enabling organizations to integrate AI that understands their specific business and data. The platform offers a comprehensive suite of features including Workspace for intelligent chat, Agent Builder for no-code automation of complex workflows, FinOps for controlling AI consumption with budgeting and reporting, and Admin for managing permissions and integrations. Additionally, its Talk feature transforms voice interactions into actionable intelligence with real-time transcription and analysis. Jeen.ai is built for resilience, security, and scalability, adapting to various industries like healthcare, defense, finance, and telco, ensuring compliance and efficiency.

Packet28 serves as a crucial context broker for AI coding agents, designed to significantly optimize their performance and reduce token consumption. By intercepting file reads, it compresses what the agent sees, turning a 9,243-line file into approximately 40 relevant lines, resulting in 164x fewer tokens on large codebases. The tool also maps the repository, building a structural understanding of files, symbols, and dependencies, allowing agents to navigate directly to relevant code. A background daemon persists context between agent restarts, enabling users to pick up where they left off without re-reading the entire project. Packet28 offers a one-command setup that auto-detects and configures popular AI coding agents like Claude Code, Cursor, Codex, Copilot, and Windsurf.

NVIDIA Launchpad AI provides access to NVIDIA NIM APIs, enabling developers to deploy and build enterprise generative AI applications using leading models. It offers free serverless APIs for development, optimized inference for various models, and the option to self-host on GPU infrastructure with continuous vulnerability fixes. Users can explore step-by-step playbooks, including setting up secure personal AI agents with NemoClaw, and design custom datasets using NeMo Data Designer. The platform features a range of open models optimized by NVIDIA's enterprise-ready inference runtime, alongside blueprints for workflows like accelerating autonomous vehicle stacks, building continuous refining AI agents, and creating intelligent agents for enterprise data.

Radicalbit offers an enterprise AI infrastructure designed to accelerate the adoption of artificial intelligence by providing a comprehensive platform for building, deploying, and governing LLM and ML models in production. It facilitates the implementation and orchestration of ML models and Generative AI applications, focusing on performance and security. The platform includes a robust AI Gateway for simplified cost and resource management, enabling the integration of AI services and models for hybrid AI use cases. Radicalbit ensures full control over AI initiatives with built-in observability and monitoring functionalities, enhancing transparency and accountability. It aims to reduce time-to-value, ensure control and compliance, and enhance scalability for AI applications.

Olvy is designed for product teams to efficiently manage user feedback, accelerating product development. It unifies customer feedback from various sources like Slack, Discord, Twitter, Telegram, Play Store, user interviews, and surveys into a single workspace. Leveraging state-of-the-art AI, Olvy automates the process of turning raw feedback into actionable insights. Key features include an AI Auto Listener Agent that intelligently identifies genuine feedback, AI-powered analysis for sentiment and thematic understanding, and tools to ask questions of qualitative data. It also offers integrations with CRMs and Zapier, and provides AI-generated reports and summaries to empower data-driven decision-making.

Weam provides a dedicated AI implementation service tailored for multi-unit businesses and franchise systems. Instead of generic AI tools, Weam offers a done-for-you approach, deploying purpose-built AI workflows directly into existing operations. This includes automating local marketing, reputation management, brand compliance, and roll-up reporting. The service aims to free up location managers from manual admin tasks, improve data-driven decision-making for HQ, and ensure consistent local execution. Weam integrates with common franchise tools like Toast, Square, Salesforce, FranConnect, and QuickBooks, offering both full-time and fractional AI engineering teams to build, monitor, and scale automated workflows.

NobodyWho is an inference engine designed to run Large Language Models (LLMs) locally and efficiently across multiple platforms, including Python, Flutter, React Native, and Godot. It offers fast and simple tool calling, automatically deriving grammars from function signatures to ensure perfect tool execution. The engine features conversation-aware preemptive context shifting, enabling long, lobotomy-free conversations. It supports optimized native code for Windows, Linux, macOS, Android, and iOS, with super-fast inference powered by Vulkan or Metal. NobodyWho is compatible with thousands of pre-trained LLMs in the GGUF format, leveraging llama.cpp, and includes vision and hearing capabilities for rich multimodal interactions. Models can be downloaded directly from Hugging Face or any URL.

MLcon serves as a global platform for the Machine Learning and Generative AI engineering community, organizing conferences and bootcamps across major cities like London, Amsterdam, San Diego, Munich, New York, and Berlin. These events bring together industry leaders and AI experts to discuss the latest advancements in machine learning, MLOps, LLMOps, and AI strategy. Attendees can enhance their skills through keynotes, workshops, and specialized bootcamps covering topics such as Generative AI, ML Fundamentals, and Full-Stack AI Engineering. MLcon also provides continuous knowledge sharing through articles, webinars, whitepapers, and cheat sheets, fostering a vibrant community for professionals to learn, share, and grow.

Shipper is an innovative AI tool designed to empower users to build a variety of applications, including web apps, mobile apps, and Chrome extensions, simply by conversing with an AI assistant. This platform eliminates the need for traditional coding, making app development accessible to non-technical users and experienced builders alike. Key features include an AI Advisor that guides the building process, pre-built templates for quick starts, and the ability to integrate functionalities like authentication, Stripe payments, map views, and host dashboards. Shipper aims to significantly accelerate the development cycle, allowing users to launch MVPs and bring ideas to life rapidly, with options for both free and paid plans that scale with usage and advanced features.

PromptPoint is an AI-powered platform designed to streamline prompt engineering for teams. It enables users to design, organize, and template prompt configurations seamlessly. The tool features an automated testing suite that provides comprehensive results in seconds, significantly boosting efficiency and ensuring high-quality LLM outputs. PromptPoint also supports versioning, deployment, and monitoring of prompt usage, allowing for precise control over prompt configurations in software applications. Its no-code platform makes prompt engineering accessible to everyone, regardless of technical background, and it offers flexibility by connecting with hundreds of large language models. A free playground is available to try out the features without requiring a credit card or sign-up.

Doclific is an open-source internal documentation tool designed to help developers and teams create beautiful, maintainable technical documentation directly within their codebase. It provides a Notion-like rich text editor supporting headings, lists, and code blocks, alongside powerful features like ERD diagramming and interactive whiteboarding for architecture designs. A key differentiator is its AI integration, which automatically adds documentation skills to Cursor and Claude AI assistants, enabling AI-powered documentation creation and editing. Doclific runs entirely on your machine, ensuring speed and data privacy, and allows for smart code snippets that automatically update with git changes, preventing scattered and outdated documentation.

Agentic-ADK is an Agent application development framework launched by Alibaba International AI Business, built upon Google-ADK and Ali-LangEngine. It is designed to simplify the development, construction, evaluation, and deployment of powerful, flexible, and controllable complex AI Agents. The framework offers features like streaming interaction, visualization debugging tools, and seamless integration with Alibaba's International Multimodal Large Language Model, Ovis, for enhanced logical reasoning and cross-language understanding. It supports flexible multi-agent frameworks with synchronous, asynchronous, streaming, and parallel execution modes, and includes a high-performance workflow engine based on Alibaba's SmartEngine. Developers can leverage hundreds of API tools, context extension for agent conversations, and prompt automation tuning.

Agentset is an open-source platform designed for building, evaluating, and deploying production-ready Retrieval Augmented Generation (RAG) and agentic applications. It provides comprehensive end-to-end tooling, covering ingestion, chunking, embeddings, and retrieval processes. The platform is model-agnostic, allowing users to integrate their preferred LLM, embeddings, and vector database. Key features include a chat playground with message editing and built-in citations, production hosting with preview links and custom domains, and a developer-friendly API with typed SDKs and OpenAPI specifications. Agentset also supports multi-tenancy and is built with modern technologies like TypeScript, Next.js, AI SDK, Prisma, Supabase, and Trigger.dev, making it a robust solution for developers.

STAT.AI is an AI-powered tool designed to significantly enhance the Stata workflow for data analysis. It enables users to perform comprehensive data analysis with greater speed and accuracy, streamlining processes that typically consume hours. A key feature is Stata GPT, which provides instant answers to complex queries, reducing the need to search through extensive documentation or forums. Additionally, STAT.AI includes converters for Python and R scripts, allowing seamless integration and conversion of code into Stata format. This makes the tool suitable for a wide range of users, from beginners seeking simplified data handling to experts looking to optimize their analytical pipelines.

Herewe Studio is a web-based 3D modeling studio designed for creating 3D games and immersive metaverse experiences. It provides an easy-to-use interface for placing objects from a user and Herewe 3D asset ecosystem into existing spatial templates. The platform boasts an advanced 3D render engine that operates directly on the web, eliminating the need for heavy local rendering software. Key features include Text-to-3D AI for spatial and avatar design, along with a comprehensive library of props, objects, and lights. Users can also extend functionality with third-party extensions like Netflix, YouTube, Spotify, and even an AI Plugin for ChatGPT GPT-4 AI Game Builder, enabling the creation of metaverse apps by combining assets and extensions.

apple-docs-mcp functions as a Model Context Protocol (MCP) server, specifically designed to integrate Apple Developer Documentation with AI assistants such as Claude, Cursor, VS Code, Windsurf, Zed, Cline, and Amazon A Developer CLI. It offers intelligent search across various Apple frameworks like SwiftUI, UIKit, Foundation, and ARKit, providing full access to Apple's JSON API for documentation, Swift/Objective-C APIs, and WWDC videos with transcripts. Developers can explore framework indexes, technology catalogs, and sample code libraries, making it an invaluable resource for AI-powered development environments. The tool also tracks documentation updates, beta APIs, and platform compatibility, enhancing the efficiency of accessing Apple's extensive developer resources.

aisearch-openai-rag-audio is an open-source sample implementation of the VoiceRAG pattern, designed to create interactive voice generative AI experiences. This tool leverages Azure AI Search for retrieval-augmented generation (RAG) and Azure OpenAI's gpt-4o-realtime-preview model for real-time audio processing and response generation. It enables developers to build applications with voice interfaces that capture audio input, process it through a RAG system, and generate audio output. Key features include voice input/output, RAG capabilities for answering questions from a knowledge base, and citations for search results. The project provides infrastructure as code and a Dockerfile for deployment to Azure Container Apps, and can also be run locally, making it a flexible solution for developers looking to integrate advanced voice AI into their applications.

airflow-ai-sdk is a Python SDK designed to seamlessly integrate Large Language Models (LLMs) and AI Agents into Apache Airflow workflows. It empowers users to define tasks that call LLMs, orchestrate multi-step AI reasoning with custom tools, and automatically parse and validate LLM outputs using type hints. The SDK supports all models available in the Pydantic AI library, including OpenAI, Anthropic, and Gemini. Key features include `@task.llm` for general LLM calls, `@task.agent` for orchestrating AI agents, `@task.llm_branch` for dynamic DAG control flow based on LLM output, and `@task.embed` for creating vector embeddings. This SDK is ideal for developers looking to leverage mature orchestration tooling like Airflow for robust, production-ready LLM and agent-based pipelines.

The Apify Model Context Protocol (MCP) server allows AI agents to leverage Apify Actors as tools for data extraction and automation. It facilitates scraping data from social media platforms, search engines, maps, e-commerce sites, and any other website using a vast library of pre-built scrapers, crawlers, and automation tools available on the Apify Store. The server supports OAuth for seamless integration with AI clients such as Claude.ai and Visual Studio Code. Key functionalities include dynamic tool discovery, agentic payments via x402 and Skyfire for Actor runs without an API token, and compatibility with various MCP clients. It offers tools for searching Actors, fetching details, calling Actors, and accessing Apify documentation and storage.

Ask Robi functions as an AI companion accessible directly via WhatsApp, offering a versatile suite of AI capabilities. Users can leverage Robi for various tasks, including generating creative images, composing textual content, translating between different languages, and receiving assistance with mathematical problems and coding challenges. The tool is designed to combine advanced AI functionalities with its own creative algorithms, aiming to provide comprehensive support with minimal setup required from the user. Its integration with WhatsApp makes it a convenient and readily available personal assistant for a wide range of daily tasks.

vly.ai is an AI-powered web development platform designed to transform user ideas into fully functional web applications. Users simply describe their project idea, and the AI agent generates, iterates, and deploys the project using React, Vite, and Convex. The platform boasts a custom real-time architecture optimized for AI compatibility, offering superior performance and cost savings, claiming to be 7x cheaper than competitors. Key features include backend visualizations that demystify AI-generated software, over 1000 integrations with popular services like Stripe, OpenAI, and GitHub, and advanced coding agents. It supports building a wide range of applications, from 3D multiplayer games and e-commerce sites to real-time collaboration tools, making it suitable for developers looking for rapid web software iteration.

BCEmbedding, developed by Netease Youdao, provides open-source embedding and reranker models specifically designed for Retrieval Augmented Generation (RAG) products. It excels in bilingual and crosslingual scenarios, supporting English, Chinese, Japanese, and Korean. The EmbeddingModel generates semantic vectors crucial for semantic search and question-answering, while the RerankerModel refines search results and ranking tasks. BCEmbedding is a cornerstone of Youdao's RAG implementation, including QAnything, and is integrated into various Youdao products. It offers high performance on semantic representation evaluations and sets new benchmarks in RAG evaluations, making it ideal for diverse RAG tasks like translation, summarization, and question answering. The models are instruction-free and user-friendly, with efficient retrieval and broad domain adaptability.

rust-genai is a comprehensive Rust library designed to simplify interaction with multiple generative AI providers through a single, ergonomic API. It natively supports a wide array of services including OpenAI, Anthropic, Gemini, xAI, Ollama, Groq, DeepSeek, Cohere, Together, Fireworks, Nebius, Mimo, Zai (Zhipu AI), BigModel, and GitHub Copilot. The library focuses on standardizing chat completion APIs, offering features like image analysis, custom authentication, model aliases, and custom endpoint resolution. It prioritizes ergonomics and commonality across services, providing native protocol support for advanced features like Gemini Thinking and Anthropic Reasoning Effort. This makes it an excellent choice for developers looking to integrate diverse AI capabilities into their Rust applications without managing multiple SDKs.