Whiz is designed to provide a robust foundation for developing intelligent agents that can perform complex conversational and task-oriented workflows. Using Whiz, developers define "tools"—Python functions or external APIs—that the agent can invoke when processing user queries. A built-in memory module captures and retrieves conversation context, enabling coherent multi-turn interactions. A dynamic planning engine decomposes goals into actionable steps, while a flexible interface allows injecting custom policies, tool registries, and memory backends. Whiz supports embedding-based semantic search to fetch relevant documents, logging for auditability, and asynchronous execution for scaling. Fully open-source, Whiz can be deployed anywhere Python runs, enabling rapid prototyping of customer support bots, data analysis assistants, or specialized domain agents with minimal boilerplate.

Doveiw is an AI-driven Chrome extension that transforms the way you interact with web content. It offers smart search functionality that interprets your queries semantically, allowing you to ask specific questions about the page you're on. Additionally, Doveiw can generate summaries, provide quick explanations, and assist with various tasks, streamlining the browsing process and enhancing your productivity. As it integrates seamlessly with supported websites, users enjoy an intuitive and responsive experience tailored to their needs.

Dust is an AI-powered platform that allows businesses to create customized virtual assistants tailored to their specific needs and workflows. The platform offers a range of features designed to improve productivity and streamline operations, enabling teams to break down knowledge silos and collaborate more effectively. By utilizing large language models and semantic search, Dust helps organizations craft optimized communications, onboard new employees, and manage data-augmented tasks efficiently.

Spark Engine uses advanced AI models to transform text data into high-dimensional vector embeddings, allowing searches to go beyond keyword matching. When a user submits a query, Spark Engine processes it through natural language understanding to capture intent, compares it with indexed document embeddings, and ranks results by semantic similarity. The platform supports filtering, faceting, typo tolerance, and result personalization. With options for customizable relevance weights and analytics dashboards, teams can monitor search performance and refine parameters. Infrastructure is fully managed and horizontally scalable, ensuring low-latency responses under high load. Spark Engine's RESTful API and SDKs for multiple languages make integration straightforward, empowering developers to embed intelligent search into web, mobile, and desktop applications rapidly.

Lilac provides robust features for exploring, filtering, clustering, and annotating data, leveraging LLM-powered insights to enhance data quality. The tool enables users to automate data transformations, remove duplicates, perform semantic searches, and detect PII, ultimately leading to superior AI performance and reliability.

Serving as a robust Go implementation of the popular LlamaIndex framework, Llama-Index-Go offers end-to-end capabilities for constructing and querying vector-based indexes from textual data. Users can load documents via built-in or custom loaders, generate embeddings using OpenAI or other providers, and store vectors in memory or external vector databases. The library exposes a QueryEngine API that supports keyword and semantic search, boolean filters, and retrieval-augmented generation with LLMs. Developers can extend parsers for markdown, JSON, or HTML, and plug in alternative embedding models. Designed with modular components and clear interfaces, it provides high performance, easy debugging, and flexible integration in microservices, CLI tools, or web applications, enabling rapid prototyping of AI-powered search and chat solutions.

Semantic Search is a Chrome extension designed to enhance your browsing experience by intelligently searching web pages for relevant information. Instead of sifting through endless results, this tool gathers textual data from the current page you're on, allowing you to get direct answers to your queries. It leverages advanced algorithms to understand the context and intent of your search, making it easier to find exactly what you need without frustration. With this extension installed, your search becomes seamless and productive, transforming the way you navigate through online content.

OpenKBS connects to your knowledge sources—PDFs, Google Drive, Notion, Slack, websites—and indexes them using advanced NLP. It then provides an AI chat agent accessible via web or embeddable widget. The agent understands user questions, retrieves relevant information, and delivers concise answers. Admins can customize appearance, configure update schedules, and monitor usage through analytics dashboards. This seamless integration streamlines support, onboarding, and documentation search across your organization.

Haystack is designed to help developers easily create custom search solutions that leverage the latest advancements in machine learning. With its components like document stores, retrievers, and readers, Haystack can connect to various data sources and effectively process queries. Its modular architecture supports mixed search strategies, including semantic search and traditional keyword-based search, making it a versatile tool for enterprises looking to enhance their search capabilities.

Trieve offers advanced AI-powered search and discovery solutions, ensuring companies have a competitive edge. Features include semantic vector search, full-text search with BM25 and SPLADE models, and hybrid search capabilities. Trieve also provides relevance tuning, sub-sentence highlighting, and robust API integrations for easy data management. Companies can manage ingestion, embeddings, and analytics effortlessly, leveraging private open-source models for maximum data security. Set up industry-leading search experiences quickly and efficiently.