Products

LlamaIndex is a data framework for your LLM applications

Keiro is a developer-first web search and scraping API designed for AI systems that need high-quality, human-written sources, not SEO spam or AI-generated junk. Unlike traditional search APIs, Keiro automatically detects and filters AI-generated content, SEO spam, and promotional pages, ensuring your LLMs are grounded in reliable, factual sources. Every result includes a 0–100 quality score, giving developers full control over what content enters their retrieval or RAG pipeline. Keiro i

Tavily is an AI-native web infrastructure platform designed to empower large language models (LLMs) and AI agents with real-time web search, content extraction, and domain crawling capabilities. By delivering structured, relevant data optimized for AI applications, Tavily enhances the performance and accuracy of AI-driven solutions. Its developer-friendly APIs and seamless integration with popular frameworks make it an essential tool for building intelligent, autonomous systems. Key Features

SEC Insights is an advanced tool designed to enhance business intelligence by simplifying the analysis of complex financial documents, including 10-K and 10-Q reports. Developed by LlamaIndex, this open-source platform enables users to extract meaningful insights from multiple documents simultaneously, facilitating comprehensive comparisons and contrasts. By providing paragraph-level citations, SEC Insights ensures precise navigation through dense financial information, offering clarity and a de

LLMLingua is a suite of prompt compression techniques designed to enhance the efficiency and performance of large language models (LLMs) by reducing the length of input prompts without significant loss of information. By intelligently compressing prompts, LLMLingua addresses challenges such as increased computational costs, latency, and context window limitations associated with lengthy inputs. Key Features and Functionality: - Coarse-to-Fine Compression: Utilizes a budget controller to mainta

Hyperbrowser is a next-generation cloud-based platform designed to empower AI agents and streamline browser automation. Tailored for AI developers, it eliminates the complexities of managing local infrastructure and performance bottlenecks, enabling users to focus on building solutions without the hassle of browser-related issues. Whether it's training AI agents for web navigation, data collection for model fine-tuning, application testing, or web scraping, Hyperbrowser facilitates the launch an

THub is a no-code AI agent orchestration platform that empowers users to build and deploy multi-agent AI workflows without any coding expertise. Designed for sectors like eCommerce, banking, and supply chain management, THub simplifies the development of generative AI applications through an intuitive drag-and-drop interface. Key Features and Functionality: - No-Code/Low-Code Development: Create production-ready generative AI applications at scale without writing code. - Drag-and-Drop Interfac

ScrapeGraphAI is an AI-powered web scraping library that leverages large language models (LLMs) and directed graph logic to create sophisticated scraping pipelines for websites and local documents, including XML, HTML, JSON, and Markdown files. By utilizing natural language prompts, users can specify the information they wish to extract, and the library automates the data retrieval process, making it accessible to users of all technical levels without the need for extensive programming knowledge

Zespan - AI Agent Reliability Platform Zespan gives engineering teams full observability into AI agents running in production. When an agent produces wrong output, costs spike, or a multi-agent workflow fails, Zespan shows exactly what happened, which tool call failed, which prompt caused the regression, which model was called, and what it cost. Distributed Tracing Every agent run is captured as a agentic trace, LLM calls, tool invocations, agent handoffs, and retrieval steps as linked spans w

Analog AI offers advanced, self-learning AI agents designed to enhance autonomous decision-making and human-like interactions. By integrating neuro-symbolic reasoning with emotional intelligence, these agents provide reliable, explainable, and empathetic responses across various applications, including customer service, healthcare, and legal sectors. Key Features and Functionality: - Neuro-Symbolic Reasoning: Combines neural networks with symbolic logic to process complex queries, reducing hal

iGPT is an Email Intelligence API that gives developers and AI builders structured, reasoning-ready context from email without building email parsing infrastructure from scratch. Connect a user's inbox via OAuth (Gmail, Outlook, IMAP). iGPT indexes the full thread and attachment history, then exposes two endpoints. The recall/ask endpoint accepts natural language queries and returns structured answers with source citations. The recall/search endpoint runs hybrid semantic and keyword search wi

RAGDrive by Nidum.Ai is an innovative, open-source application that brings the power of advanced Large Language Models (LLMs) directly to your local device. By integrating Retrieval-Augmented Generation (RAG) with LlamaIndex technology, RAGDrive enables intelligent, context-aware AI solutions without the need for internet connectivity. Its user-friendly, no-code interface allows seamless interaction with various document types through conversational interfaces, making complex tasks like financia

The Agent Governance Toolkit is an open-source runtime security framework designed to enforce deterministic policies for autonomous AI agents. It operates by intercepting every agent action—such as tool calls, API requests, and inter-agent messages—before execution, ensuring compliance with predefined policies at sub-millisecond latency. This toolkit addresses all ten risks identified in the OWASP Agentic AI Top 10, providing a comprehensive governance solution for AI agents. Key Features and F

InfraBase.ai is a comprehensive directory designed to assist developers, businesses, and AI enthusiasts in discovering and comparing a wide range of AI infrastructure tools and services. By curating an extensive list of products across various categories, InfraBase.ai simplifies the process of identifying the most suitable solutions for AI projects, enabling users to build world-class AI applications efficiently. Key Features and Functionality: - Vector Databases: Explore platforms like Zilliz

Prediction Guard is a platform that enables organizations to deploy, manage, and scale private AI systems within their own infrastructure, ensuring data security and compliance with AI security best practices. By operating behind the organization's firewall, Prediction Guard allows enterprises to harness the transformative power of AI without compromising sensitive information. Key Features and Functionality: - Flexible Deployment: Supports on-premises, air-gapped, hybrid, and cloud Virtual Pr

Oculis by Selaware is a comprehensive monitoring and management platform designed to provide organizations with full visibility into their AI agents. It enables users to oversee costs, health, performance, and interrelationships of AI agents without requiring code modifications. By deploying a single collector, Oculis automatically detects and monitors AI agents across various frameworks, offering real-time insights and analytics. Key Features and Functionality: - Agent Discovery: Automaticall

We built ICE at Dopove after watching teams hit the same wall repeatedly: an LLM system works fine in demos, then degrades in production because the model cannot reliably hold, retrieve, and attend to the right context over long workflows. The pain shows up as specific failures, not abstract architecture concerns: - "The agent completed steps 1–5, then forgot the result of step 2." - "We hacked together pgvector, Redis, summaries, and session state — now nobody trusts it." - "If this ever lea

fastCRW is an open-source web scraping, crawling, search, and data extraction API distributed as a single Rust binary. It exposes a /v1 HTTP API compatible with the Firecrawl request and response format, and a search endpoint compatible with the Tavily response format, allowing existing client SDKs to connect by changing only the base URL. The product provides four primary endpoints. Scrape fetches a single URL and returns the page as structured markdown along with metadata, optional screenshot

LlamaParse is an advanced document parsing service designed to convert complex, unstructured documents into formats optimized for Large Language Models (LLMs). It efficiently processes various document types, including PDFs, Word documents, PowerPoint presentations, and spreadsheets, extracting meaningful information from elements like tables, charts, images, and flow diagrams. This transformation streamlines workflows, allowing users to focus on data utilization rather than data wrangling.

Agents-Flex is a Java-based AI application development framework designed to simplify the creation of AI applications. Inspired by LangChain and LlamaIndex, it offers portable API support across various AI service providers, independent of specific Java development frameworks. Agents-Flex is suitable for a range of scenarios, including chat, image generation, embedding models, function calling, and retrieval-augmented generation (RAG) applications, supporting both synchronous and streaming API o