Coding & Development

prompttools, created by Hegel AI, is an open-source, self-hostable toolkit designed for experimenting with, testing, and evaluating large language models (LLMs), vector databases, and prompts. It enables developers to test prompts and parameters across various models, including OpenAI, Anthropic, and LLaMA, and to assess the retrieval accuracy of vector databases. The tool offers evaluation through code, notebooks, and a local playground interface. It supports a wide range of integrations for LLMs like OpenAI, LLaMA.Cpp, HuggingFace, Anthropic, Mistral AI, Google Gemini, and Google PaLM, as well as vector databases such as Chroma, Weaviate, Qdrant, LanceDB, Milvus, Pinecone, and Epsilla. Users can persist results by exporting experiments to CSV, JSON, or MongoDB.

CloudKeeper Tuner is an automated AWS usage optimization platform designed to help businesses achieve the lowest possible cloud costs without compromising performance. It acts as a real-time assistant for smarter AWS cost and usage optimization, seamlessly integrating into existing workflows across multiple AWS accounts. The platform delivers tailored recommendations, enabling effortless resource optimization while ensuring peak performance for AWS workloads. Key features include identifying zombie and unused resources, detecting and optimizing over-allocated compute and storage services, and recommending upgrades to the latest AWS resources for better performance and savings. It also offers a Scheduler to automatically shut down idle cloud resources and a SpotBot for dynamic switching between Spot and On-Demand instances to save up to 65%. CloudKeeper Tuner provides 150+ real-time recommendations across 50+ AWS services, with an average savings of 10% within the first 30 days of onboarding.

Oraichain Labs is a pioneering AI Layer 1 blockchain platform established in 2020, offering comprehensive frameworks and tools for integrating human-centric artificial intelligence with decentralized infrastructures. The platform is dedicated to advancing AI blockchain oracle technology and fostering cross-chain interoperability, paving the way for the mass adoption of next-generation Web3 applications. Its dynamic ecosystem supports a wide range of products across DeFi, NFTs, Identity, Collective Intelligence, Asset Tokenization, and Smart Healthcare. Oraichain provides resources for developers, including technical support, business development aid, and funding for innovative ideas, making it a robust environment for building and scaling AI-driven decentralized solutions.

ROMA (Recursive-Open-Meta-Agent) is an open-source framework designed to simplify the creation of hierarchical, high-performance multi-agent systems. It employs a recursive plan-execute loop, breaking down complex tasks into parallelizable components for efficient problem-solving. Key features include an Atomizer to determine task atomicity, a Planner for subtask decomposition, Executors for handling atomic tasks, and an Aggregator to synthesize results. ROMA supports various LLM providers, offers built-in toolkits like Calculator and File operations, and provides flexible installation options from a minimal setup for quick evaluation to a full Dockerized production environment with persistence, observability, and a REST API.

rubberduck-vscode is an open-source Visual Studio Code extension designed to enhance the developer experience with AI-powered code assistance. Leveraging the OpenAI API, it offers functionalities such as intelligent code editing, detailed explanations of code snippets, and efficient code generation directly within the VS Code environment. The tool also aids in error diagnosis and bug finding through an interactive AI chat interface, streamlining the debugging process. Its integration into a popular IDE makes it a convenient solution for developers looking to accelerate their coding workflows and improve code quality with AI.

Ash is a macOS sandbox specifically designed to secure AI coding agents by restricting their system-level access. It limits an agent's interaction with files, networks, processes, IO devices, and environment variables, mitigating risks associated with AI agents potentially causing accidental or malicious damage to sensitive data. Users can define granular policies to control what resources an agent can use, ensuring the agent and its subprocesses operate within defined boundaries. This fine-grained security control covers filesystem access (read, write, create, delete), network connections (by host and port), process execution, and access to hardware like USB ports, cameras, and microphones. Ash helps developers safely integrate AI coding agents into their workflows.

semantic-search-nextjs-pinecone-langchain-chatgpt is a foundational starter project designed for developers looking to build semantic search applications. This open-source tool facilitates the process of embedding text files into vectors, storing these vectors in a Pinecone database, and then performing semantic searches using GPT3 and Langchain, all within a Next.js user interface. It aims to simplify the integration of these powerful AI and database technologies, providing a cohesive starting point for projects that require advanced natural language understanding and contextual search capabilities. The project is particularly useful for those who understand individual components but need guidance on piecing them together into a functional application.

Solana-agent-kit is an open-source toolkit designed to bridge AI agents with Solana blockchain protocols. It allows any AI agent, regardless of the underlying model, to autonomously perform a wide array of Solana actions. These capabilities span over 60 distinct operations, including deploying and trading tokens, launching new tokens, lending assets, and sending compressed airdrops. The kit offers extensive features for token operations, NFT management, and DeFi integration with platforms like Jupiter Exchange, Raydium, and Orca. It also includes AI integration features such as LangChain and Vercel AI SDK support, autonomous modes, and built-in error handling, making it a comprehensive solution for developers building AI-powered applications on Solana.

SolidUI is an innovative open-source project that combines natural language processing (NLP) with computer graphics to enable the generation of various visualization types from a single sentence. It aims to help users quickly build visualization tools, including 2D, 3D, and 3D scenes, facilitating rapid construction of 3D data presentation scenarios. SolidUI utilizes a self-developed Vincent graph language model, trained on extensive text and graphics data, and optimized through the RLHF (Reinforcement Learning Human Feedback) process to ensure high-quality and accurate graph generation. Key features include a minimalist design, support for multiple data sources, integration with Huggingface space, and compatibility with Large Language Models.

API4AI provides a suite of AI-powered, cloud-native image processing APIs designed to boost product functionality and automate business processes. Users can access a wide range of services including Background Removal, Optical Character Recognition (OCR), NSFW Content Moderation, Image Labelling, Face Recognition, Brand Mark Detection, and Image Anonymization. The platform offers a unified HTTP API, making it intuitive and easy for developers to integrate these solutions into their applications. API4AI caters to enterprises seeking to extract information and automate operations, startups looking to accelerate MVP development, and developers needing ready-to-use APIs. Access is available through their Developer Portal or RapidAPI, with a pay-as-you-go or subscription-based model.

Appian is a leading low-code automation platform that leverages AI to orchestrate complex business processes across the enterprise. It provides a unified platform for designing, automating, and optimizing business operations, integrating technologies like Robotic Process Automation (RPA), Intelligent Document Processing (IDP), and API integrations. The platform features AI agents and copilots to drive business value and offers AI-augmented development capabilities. Appian's Data Fabric unifies data silos, while its Process Intelligence tools allow for comprehensive analysis and reporting. It's designed to accelerate business with packaged applications for various industries, including financial services, insurance, public sector, and life sciences, helping organizations modernize systems and improve operational efficiency.

sktime is a comprehensive open-source Python library designed for machine learning with time series data. It offers a unified interface for various time series learning tasks, including forecasting, time series classification, clustering, anomaly detection, and changepoint detection. The framework comes equipped with dedicated time series algorithms and scikit-learn compatible tools, enabling users to build, tune, and validate time series models efficiently. sktime also enhances interoperability by providing interfaces to related libraries such as scikit-learn, statsmodels, tsfresh, PyOD, and fbprophet, facilitating composite model building through features like pipelining, ensembling, tuning, and reduction.

StreamRAG is an open-source video search and streaming agent designed to work with ChatGPT, enabling users to efficiently search and retrieve specific content directly from videos. This tool facilitates the seamless integration of video data into conversational AI applications, significantly enhancing the capabilities of AI agents by providing them with rich, dynamic media context. By allowing AI to understand and interact with video content, StreamRAG opens up new possibilities for advanced information retrieval and interactive experiences within AI-driven platforms. Its open-source nature promotes community contributions and flexible deployment, making it a versatile solution for developers looking to augment their AI agents with powerful video intelligence.

Jabuti AGI is a platform for Agentic AI designed for digital customer relationship channels, particularly in regulated markets. It provides autonomous AI agents for WhatsApp, chat, and email that can understand context, make decisions, and execute actions securely. The platform is built for critical production journeys, offering banking-level security, full integration with corporate systems, and scalability for millions of interactions daily. Key features include governance with defined rules, 100% auditable trails, and real-time token consumption monitoring for cost control. Jabuti AGI aims to reduce operational costs, decrease callbacks, and minimize human intervention while improving customer experience and generating strategic insights.

Swark is an open-source VS Code extension designed to automatically generate architecture diagrams from your codebase. Leveraging large language models (LLMs) via GitHub Copilot, it simplifies the process of visualizing code structure without requiring any authentication or API keys. This tool is particularly useful for developers looking to quickly understand new or legacy codebases, review AI-generated code, or improve documentation with up-to-date diagrams. Swark supports all programming languages, as the diagram generation logic is encapsulated within the LLM, making it highly versatile. It outputs diagrams in Mermaid.js format, allowing for easy editing and refinement.

Scott AI is an agentic workspace designed to enhance collaboration and efficiency when working with coding agents. It serves as an alignment layer between development teams and their AI coding agents, helping product teams define comprehensive specifications and gain team approval before delegation. The platform aims to reduce token waste, minimize misaligned agent output, and mitigate stability risks by ensuring agents execute on approved intent rather than assumptions. Scott AI integrates with existing codebases and knowledge sources, providing a 'planspace' for developing proposals and a streamlined review process with inline comments and prototype sharing. It is agnostic to the specific coding agents used, allowing teams to delegate approved plans with full context to any agent.

text-generation-webui-extensions serves as a comprehensive directory for extensions designed to enhance the text-generation-webui. This resource enables users to significantly expand the capabilities and personalize the user interface of their text generation setups. The available extensions cover a wide range of functionalities, including Discord bots for both text and image generation, offering advanced features for various applications. The platform also encourages community contribution, allowing users to submit their own extensions to the growing list, fostering a collaborative environment for development and customization. This makes it a valuable hub for anyone looking to optimize and tailor their text generation experience.

TheWhisper is an open-source project dedicated to developing highly efficient speech-to-text and text-to-speech inference solutions, with a strong emphasis on self-hosting, cloud hosting, and on-device inference across various platforms. It provides optimized Whisper models with streaming inference support, offering flexible chunk sizes (10s, 15s, 20s, 30s) unlike the original 30s fixed size. The tool features high-performance inference engines for NVIDIA GPUs and CoreML engines for macOS/Apple Silicon, known for their low power consumption. It's ideal for real-time captioning, live meetings, voice interfaces, and edge deployments, and includes a local RestAPI with frontend examples and a demo Electron app for macOS.

tenere is a TUI (Text-based User Interface) designed for seamless interaction with various Large Language Models (LLMs). It offers a robust set of features including syntax highlighting for improved readability, comprehensive chat history management, and the ability to save conversations to files for future reference. The tool is highly customizable, supporting Vim keybindings for efficient navigation and integrated clipboard functionality. A key differentiator of tenere is its versatility, as it supports multiple LLM backends, including popular options like ChatGPT, llama.cpp, and ollama, allowing users to switch between different models based on their needs. This makes it a powerful and flexible solution for developers and researchers working with conversational AI.

Goalcrafts offers an AI-native agent service designed to revolutionize quality assurance by providing automated testing, reducing costs, and accelerating release cycles. It operates on a pay-for-results model, eliminating billable hours and SaaS fees. The service provides smart test orchestration and execution with AI-driven insights for optimal test coverage, zero infrastructure overhead, and 24/7 automated business use-case monitoring. Goalcrafts emphasizes a shift from manual testing, offering faster execution, higher accuracy, and cost-effectiveness through automated and reusable tests. It addresses common test automation hurdles like increasing complexity, scaling infrastructure, talent shortages, and delayed releases by leveraging AI-powered planning, execution, maintenance, and reporting.

FortyAU is a Nashville-based software development company offering innovative software and AI services at scale. They provide a full suite of digital services, from intelligent AI pipelines to custom enterprise software, designed to drive business value and company growth. Their expertise spans data & AI, software engineering, cloud & DevOps, and product & design. FortyAU is particularly trusted by healthcare and highly regulated industries, with over 90% of their projects in these sectors. They pride themselves on a partnership model, ensuring continuity of teams who deeply understand each client’s business, and hiring top tech talent.

Quantiphi is an AI-first digital engineering company dedicated to helping enterprises reimagine and realize transformational opportunities in the AI era. The company specializes in AI-first digital engineering, combining industry experience with advanced cloud and data engineering practices, and cutting-edge AI research. Quantiphi aims to solve complex business problems by leveraging artificial intelligence, driving accelerated and quantifiable business results for its clients. Their approach focuses on enabling businesses to adapt and thrive through digital transformation powered by AI.

PARADOX CAT GmbH is a software development company specializing in Human Machine Interface (HMI) software, AI, and Machine Learning projects, with a strong focus on real-time graphics for the automotive segment. Since 2009, they have supported premium automotive manufacturers in implementing next-generation HMI software, driving innovation and setting industry standards. Their expertise extends to Android HMI, in-cabin sensing, and 3D graphics. The company also has a dedicated AI department, PARADOX AI, aimed at enabling clients to conduct innovative AI/ML research, rapidly prototype, and successfully integrate new technologies into vehicles. Their philosophy is rooted in an agile mindset, delivering functional software with continuous quality control. Beyond automotive, PARADOX CAT serves the aviation, maritime, and space industries with specialized HMI and AI solutions.

V88 delivers production-grade AI solutions built within Daia, their proven Deployed AI Architecture. They offer bespoke AI applications, workflow automation, data integration, and no-code solutions tailored to specific business challenges. V88 also provides sector-specific platforms for regulated industries like local government and care homes. Leveraging their expertise as the #1 Glide Agency globally, they build custom business apps, dashboards, and workflow automations without writing code, ensuring scalability and resilience. The company emphasizes engineering integrity, ISO 27001 accreditation, and a structured build pipeline for robust and scalable solutions, moving beyond experimental prototypes to deliver real-world results for enterprises.