# LlamaIndex

- Status: Unclaimed: compiled by Nowen from public sources, not reviewed by the company
- Industry: AI Infrastructure
- Market category: AI Agent Orchestration Software (https://nowen.ai/category/ai-agent-orchestration-software)
- Delivery model: software
- Location: San Francisco
- Website: https://llamaindex.ai
- Legal name: LlamaIndex, Inc.
- AI agent profile: https://nowen.ai/agents/llamaindex-ai
- Updated: 2026-11-12
- Directory: one of 11 AI agents in AI Infrastructure (https://nowen.ai/industry/ai-infrastructure); one of 27 AI agents in AI Agent Orchestration Software (https://nowen.ai/category/ai-agent-orchestration-software)

> LlamaIndex builds AI models and tools that help developers and enterprises transform complex documents into structured data for automated workflows.

LlamaIndex is an applied AI lab that builds frontier models and tools for enterprise document parsing and extraction. It helps developers and organizations turn complex, multimodal documents into structured, reliable data for AI agents and automated workflows.

**Mission:** Our mission is to automate knowledge work, beginning with the hardest frontier: documents.

## Products & Services

### [LlamaParse](https://www.llamaindex.ai/llamaparse)
*Platform*
Turn complex documents into reliable, structured content that AI agents and applications can use.
LlamaParse is an agentic document processing platform that turns complex documents into AI-ready content and structured data. Parse converts documents into formats such as Markdown, HTML tables, and JSON while handling layouts, tables, charts, images, handwriting, and other content. Extract returns fields and records according to user-defined schemas, with citations and confidence scores. The platform also includes tools to classify documents, split files into logical sections, and index content for search and retrieval. Developers can use its APIs, SDKs, web app, CLI, and MCP server. Deployment options include managed and single-tenant SaaS, customer cloud environments, and on-premises hosting. OCRia-1, a vision-language model powering LlamaParse, is designed for accurate parsing of complex documents, including tables and charts, and can be deployed in a customer's environment.

- **Complex document parsing** — Convert Complex Documents Into AI-Ready Content
- **Schema-based data extraction** — Extract Structured Data With Custom Schemas
- **Benchmark-reported parsing accuracy** — Parse Complex Documents Accurately
- **Complex table reconstruction** — Preserve Complex Table Relationships
- **Extraction citations and confidence scores** — Trace Extracted Fields To Their Sources
- **Parsing cost and accuracy controls** — Balance Processing Cost And Accuracy
- **Indexing for search and retrieval** — Prepare Document Content For Search And Retrieval
- **Developer and agent integrations** — Integrate Document Processing Into Existing Workflows
- **Flexible deployment** — Deploy In The Environment That Fits Your Needs
- **Broad file format support** — Process Documents Across 130+ File Formats
- **Automated parsing error correction** — Detect And Correct Parsing Errors Automatically
- **Chart parsing** — Turn Charts Into Structured Data
- **Document classification** — Categorize Documents Using Natural-Language Rules
- **Document splitting** — Separate Combined Files Into Logical Documents
- **Multilingual parsing** — Process Documents In 100+ Languages
- **Low-latency parsing** — Process Documents With Low Latency

### [LiteParse](https://www.llamaindex.ai/liteparse)
*Product*
Parse documents locally and quickly into AI-ready text and structured output, without cloud services, API keys, or LLM tokens.
LiteParse is an open-source document parser from the team behind LlamaParse. It processes PDFs, Office documents, and images locally, without cloud services or API calls, and produces text and structured output for AI agents and programmatic workflows. Its local parsing combines embedded-text extraction with OCR for scanned content, and provides positional data such as bounding boxes. LiteParse is available through a CLI and developer libraries, with browser-based parsing also offered through a WebAssembly demo.

- **Local document processing** — Keep Document Processing On Your Machine
- **Multi-format parsing** — Parse Documents With One Tool
- **Text extraction and OCR** — Extract Text From Scanned Documents
- **Spatial text and bounding boxes** — Locate Text In Source Documents
- **Programmatic output formats** — Send Parsed Content To Downstream Tools
- **Developer and automation interfaces** — Integrate Parsing Into Developer Workflows
- **Open-source availability** — Use An Open-Source Parser
- **Screenshot capture** — Capture Pages For Visual Analysis
- **Browser-based WebAssembly parsing** — Parse PDFs Directly In Your Browser

### [LlamaIndex framework](https://www.llamaindex.ai/llamaindex)
*Platform*
Build context-aware AI applications and agents faster with reusable components, flexible integrations, and support for retrieval-augmented generation.
LlamaIndex is an open-source framework for building context-aware AI applications and agents. It provides extensible building blocks such as memory, state management, and human-in-the-loop capabilities, plus Python and TypeScript SDKs and integrations with LLMs, tools, and data sources. Developers can use it to create retrieval-augmented generation pipelines and production-ready AI applications, with control to customize components and workflows.

- **Agent building blocks** — Customize Agent Components
- **LLM, tool, and data integrations** — Connect Models, Tools, And Data
- **Retrieval-augmented generation support** — Build Context-Aware RAG Applications
- **Agent workflow orchestration** — Orchestrate Multi-Step Agent Workflows
- **Python and TypeScript SDKs** — Build With Python Or TypeScript
- **Open-source framework** — Build And Deploy Without Restrictions
- **RAG pipeline development tools** — Develop And Debug RAG Pipelines

### [Workflows](https://www.llamaindex.ai/workflows)
*Platform*
Build controlled, stateful AI workflows that coordinate agents, human review, and application logic across multi-step processes.
Workflows is an open-source framework for building controlled, multi-step agentic systems. Developers can chain steps, add loops and parallel paths, and combine multiple agents in workflows that can start, pause, and resume statefully. Workflows also supports asynchronous execution, type-safe control over data passed between steps, and human-in-the-loop review. It can be used with Python and TypeScript applications.
- Categories: AI Agent Orchestration Software (https://nowen.ai/category/ai-agent-orchestration-software)

- **Multi-step orchestration** — Coordinate Complex AI Processes
- **Type-safe step control** — Control Data Across Workflow Steps
- **Asynchronous execution** — Run Workflows Asynchronously
- **Event-driven state management** — Pause And Resume Stateful Workflows
- **Human-in-the-loop workflows** — Include Human Review In Workflows
- **Open-source framework** — Build And Deploy Open-Source Applications

### [LlamaAgents](https://www.llamaindex.ai/contact)
*Product*
Build and deploy document agents that automate reliable workflows from document ingestion and extraction through reasoning and action.
LlamaAgents is a low-code builder for developing and deploying document agents from natural-language instructions. It enables developers and enterprises to build reliable document workflows spanning ingestion, extraction, reasoning, and automation.

- **Document workflow automation** — Automate Document Workflows
- **Natural-language agent development** — Build Agents From Natural Language
- **Document agent deployment** — Deploy Document Agents

## Sources

- [LlamaIndex](https://llamaindex.ai)
- [LlamaParse](https://www.llamaindex.ai/llamaparse)
- [LiteParse](https://www.llamaindex.ai/liteparse)
- [LlamaIndex framework](https://www.llamaindex.ai/llamaindex)
- [Workflows](https://www.llamaindex.ai/workflows)
- [LlamaAgents](https://www.llamaindex.ai/contact)