Skip to content
J·BJon BishopFractional growth marketer

Artificial intelligence · llms.txt file breakdown

CrewAI llms.txt

A directly retrieved Markdown index for CrewAI's documentation, with 225 links across 4 detected headings.

The actual file

Source Markdown

The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.

Open saved text ↗

Showing the first 18000 characters. Load the complete file to read the remainder.

# CrewAI

## Docs

- [CrewAI Documentation](https://docs.crewai.com/index.md): Build collaborative AI agents, crews, and flows — production ready from day one.
- [Introduction](https://docs.crewai.com/v1.15.28/en/introduction.md): Build AI agent teams that work together to tackle complex tasks
- [Build with AI](https://docs.crewai.com/v1.15.28/en/guides/coding-tools/build-with-ai.md): Everything AI coding agents need to build, deploy, and scale with CrewAI — skills, machine-readable docs, deployment, and enterprise features.
- [Skills](https://docs.crewai.com/v1.15.28/en/skills.md): Install crewaiinc/skills from the official registry at skills.sh—Flows, Crews, and docs-aware agents for Claude Code, Cursor, Codex, and more.
- [Installation](https://docs.crewai.com/v1.15.28/en/installation.md): Get started with CrewAI - Install, configure, and build your first AI crew
- [Quickstart](https://docs.crewai.com/v1.15.28/en/quickstart.md): Build your first CrewAI Flow in minutes — orchestration, state, and an agent crew that produces a real report.
- [Evaluating Use Cases for CrewAI](https://docs.crewai.com/v1.15.28/en/guides/concepts/evaluating-use-cases.md): Learn how to assess your AI application needs and choose the right approach between Crews and Flows based on complexity and precision requirements.
- [Crafting Effective Agents](https://docs.crewai.com/v1.15.28/en/guides/agents/crafting-effective-agents.md): Learn best practices for designing powerful, specialized AI agents that collaborate effectively to solve complex problems.
- [Build Your First Crew](https://docs.crewai.com/v1.15.28/en/guides/crews/first-crew.md): Step-by-step tutorial to create a collaborative AI team with JSON-first crew configuration.
- [Build Your First Flow](https://docs.crewai.com/v1.15.28/en/guides/flows/first-flow.md): Learn how to create structured, event-driven workflows with precise control over execution.
- [Mastering Flow State Management](https://docs.crewai.com/v1.15.28/en/guides/flows/mastering-flow-state.md): A comprehensive guide to managing, persisting, and leveraging state in CrewAI Flows for building robust AI applications.
- [Conversational Flows](https://docs.crewai.com/v1.15.28/en/guides/flows/conversational-flows.md): Build multi-turn chat apps with handle_turn per turn, message history, intent routing, tracing, and structured streaming.
- [Migrating from inputs.id to restore_from_state_id](https://docs.crewai.com/v1.15.28/en/guides/flows/inputs-id-deprecation.md): Move @persist flows off the deprecated inputs.id hydration onto the supported restore_from_state_id field
- [Frontend Overview](https://docs.crewai.com/v1.15.28/en/guides/frontend/overview.md): Build interactive user interfaces for your CrewAI agents with CopilotKit and the AG-UI protocol.
- [Conversational Flows](https://docs.crewai.com/v1.15.28/en/guides/frontend/conversational-flows.md): Serve native, session-aware CrewAI Flows over AG-UI with managed conversation state and full frontend parity.
- [Generative UI](https://docs.crewai.com/v1.15.28/en/guides/frontend/generative-ui.md): Render your CrewAI agent's work as live React components, across the full spectrum from author-controlled to agent-invented UI.
- [Tool-Based Generative UI](https://docs.crewai.com/v1.15.28/en/guides/frontend/tool-based-generative-ui.md): Map a CrewAI agent's tool calls to React components and stream the arguments in as they arrive.
- [Agentic Generative UI](https://docs.crewai.com/v1.15.28/en/guides/frontend/agentic-generative-ui.md): Render your CrewAI Flow's live state as UI that updates as the agent works through multi-step tasks.
- [Reasoning](https://docs.crewai.com/v1.15.28/en/guides/frontend/reasoning.md): Show the model's thinking in the chat automatically, with no component to build.
- [A2UI](https://docs.crewai.com/v1.15.28/en/guides/frontend/a2ui.md): The declarative tier of generative UI — the agent assembles a surface from a catalog of components you own.
- [Human-in-the-Loop](https://docs.crewai.com/v1.15.28/en/guides/frontend/human-in-the-loop.md): Pause your CrewAI agent mid-run to collect a user decision, then resume the agent with their answer.
- [Shared State](https://docs.crewai.com/v1.15.28/en/guides/frontend/shared-state.md): Keep your CrewAI agent's state and your app's UI in two-way sync, so edits on either side flow to the other.
- [Frontend Actions](https://docs.crewai.com/v1.15.28/en/guides/frontend/frontend-actions.md): Let your CrewAI agent call functions that run in the user's browser, from switching themes to navigating your app.
- [Predictive State Updates](https://docs.crewai.com/v1.15.28/en/guides/frontend/predictive-state-updates.md): Stream an in-progress tool call's arguments into agent state so the UI updates optimistically while the agent is still generating.
- [Channels](https://docs.crewai.com/v1.15.28/en/guides/frontend/channels.md): Run the same CrewAI agent as a Slack or Teams bot with the CopilotKit Channels SDK and managed Intelligence platform.
- [Publish Custom Tools](https://docs.crewai.com/v1.15.28/en/guides/tools/publish-custom-tools.md): How to build, package, and publish your own CrewAI-compatible tools to PyPI so any CrewAI user can install and use them.
- [Coding Tools](https://docs.crewai.com/v1.15.28/en/guides/coding-tools/agents-md.md): Use AGENTS.md to guide coding agents and IDEs across your CrewAI projects.
- [Customizing Prompts](https://docs.crewai.com/v1.15.28/en/guides/advanced/customizing-prompts.md): Dive deeper into low-level prompt customization for CrewAI, enabling super custom and complex use cases for different models and languages.
- [Fingerprinting](https://docs.crewai.com/v1.15.28/en/guides/advanced/fingerprinting.md): Learn how to use CrewAI's fingerprinting system to uniquely identify and track components throughout their lifecycle.
- [Moving from LangGraph to CrewAI: A Practical Guide for Engineers](https://docs.crewai.com/v1.15.28/en/guides/migration/migrating-from-langgraph.md): If you already have built with LangGraph, learn how to quickly port your projects to CrewAI
- [Upgrading CrewAI](https://docs.crewai.com/v1.15.28/en/guides/migration/upgrading-crewai.md): How to upgrade CrewAI in your project and adapt to breaking changes between versions.
- [Agents](https://docs.crewai.com/v1.15.28/en/concepts/agents.md): Detailed guide on creating and managing agents within the CrewAI framework.
- [Agent Capabilities](https://docs.crewai.com/v1.15.28/en/concepts/agent-capabilities.md): Understand the five ways to extend CrewAI agents: Tools, MCPs, Apps, Skills, and Knowledge.
- [Tasks](https://docs.crewai.com/v1.15.28/en/concepts/tasks.md): Detailed guide on managing and creating tasks within the CrewAI framework.
- [Crews](https://docs.crewai.com/v1.15.28/en/concepts/crews.md): Understanding and utilizing crews in the crewAI framework with comprehensive attributes and functionalities.
- [Flows](https://docs.crewai.com/v1.15.28/en/concepts/flows.md): Learn how to create and manage AI workflows using CrewAI Flows.
- [Streaming](https://docs.crewai.com/v1.15.28/en/concepts/streaming.md): Understand CrewAI's streaming model for Flows, direct LLM calls, tools, and conversational turns.
- [Production Architecture](https://docs.crewai.com/v1.15.28/en/concepts/production-architecture.md): Best practices for building production-ready AI applications with CrewAI
- [Knowledge](https://docs.crewai.com/v1.15.28/en/concepts/knowledge.md): What is knowledge in CrewAI and how to use it.
- [Skills](https://docs.crewai.com/v1.15.28/en/concepts/skills.md): Filesystem-based skill packages that inject domain expertise and instructions into agent prompts.
- [LLMs](https://docs.crewai.com/v1.15.28/en/concepts/llms.md): A comprehensive guide to configuring and using Large Language Models (LLMs) in your CrewAI projects
- [Files](https://docs.crewai.com/v1.15.28/en/concepts/files.md): Pass images, PDFs, audio, video, and text files to your agents for multimodal processing.
- [Processes](https://docs.crewai.com/v1.15.28/en/concepts/processes.md): Detailed guide on workflow management through processes in CrewAI, with updated implementation details.
- [Collaboration](https://docs.crewai.com/v1.15.28/en/concepts/collaboration.md): How to enable agents to work together, delegate tasks, and communicate effectively within CrewAI teams.
- [Training](https://docs.crewai.com/v1.15.28/en/concepts/training.md): Learn how to train your CrewAI agents by giving them feedback early on and get consistent results.
- [Memory](https://docs.crewai.com/v1.15.28/en/concepts/memory.md): Leveraging the unified memory system in CrewAI to enhance agent capabilities.
- [Reasoning](https://docs.crewai.com/v1.15.28/en/concepts/reasoning.md): Learn how to enable and use agent reasoning to improve task execution.
- [Planning](https://docs.crewai.com/v1.15.28/en/concepts/planning.md): Learn how to add planning to your CrewAI Crew and improve their performance.
- [Testing](https://docs.crewai.com/v1.15.28/en/concepts/testing.md): Learn how to test your CrewAI Crew and evaluate their performance.
- [CLI](https://docs.crewai.com/v1.15.28/en/concepts/cli.md): Learn how to use the CrewAI CLI to interact with CrewAI.
- [Tools](https://docs.crewai.com/v1.15.28/en/concepts/tools.md): Understanding and leveraging tools within the CrewAI framework for agent collaboration and task execution.
- [Event Listeners](https://docs.crewai.com/v1.15.28/en/concepts/event-listener.md): Tap into CrewAI events to build custom integrations and monitoring
- [Checkpointing](https://docs.crewai.com/v1.15.28/en/concepts/checkpointing.md): Automatically save execution state so crews, flows, and agents can resume after failures.
- [MCP Servers as Tools in CrewAI](https://docs.crewai.com/v1.15.28/en/mcp/overview.md): Learn how to integrate MCP servers as tools in your CrewAI agents using the `crewai-tools` library.
- [MCP DSL Integration](https://docs.crewai.com/v1.15.28/en/mcp/dsl-integration.md): Learn how to use CrewAI's simple DSL syntax to integrate MCP servers directly with your agents using the mcps field.
- [Stdio Transport](https://docs.crewai.com/v1.15.28/en/mcp/stdio.md): Learn how to connect CrewAI to local MCP servers using the Stdio (Standard Input/Output) transport mechanism.
- [SSE Transport](https://docs.crewai.com/v1.15.28/en/mcp/sse.md): Learn how to connect CrewAI to remote MCP servers using Server-Sent Events (SSE) for real-time communication.
- [Streamable HTTP Transport](https://docs.crewai.com/v1.15.28/en/mcp/streamable-http.md): Learn how to connect CrewAI to remote MCP servers using the flexible Streamable HTTP transport.
- [Connecting to Multiple MCP Servers](https://docs.crewai.com/v1.15.28/en/mcp/multiple-servers.md): Learn how to use MCPServerAdapter in CrewAI to connect to multiple MCP servers simultaneously and aggregate their tools.
- [MCP Security Considerations](https://docs.crewai.com/v1.15.28/en/mcp/security.md): Learn about important security best practices when integrating MCP servers with your CrewAI agents.
- [Tools Overview](https://docs.crewai.com/v1.15.28/en/tools/overview.md): Discover CrewAI's extensive library of 40+ tools to supercharge your AI agents
- [Overview](https://docs.crewai.com/v1.15.28/en/tools/file-document/overview.md): Read, write, and search through various file formats with CrewAI's document processing tools
- [File Read](https://docs.crewai.com/v1.15.28/en/tools/file-document/filereadtool.md): The `FileReadTool` is designed to read files from the local file system.
- [File Write](https://docs.crewai.com/v1.15.28/en/tools/file-document/filewritetool.md): The `FileWriterTool` is designed to write content to files.
- [PDF RAG Search](https://docs.crewai.com/v1.15.28/en/tools/file-document/pdfsearchtool.md): The `PDFSearchTool` is designed to search PDF files and return the most relevant results.
- [DOCX RAG Search](https://docs.crewai.com/v1.15.28/en/tools/file-document/docxsearchtool.md): The `DOCXSearchTool` is a RAG tool designed for semantic searching within DOCX documents.
- [MDX RAG Search](https://docs.crewai.com/v1.15.28/en/tools/file-document/mdxsearchtool.md): The `MDXSearchTool` is designed to search MDX files and return the most relevant results.
- [XML RAG Search](https://docs.crewai.com/v1.15.28/en/tools/file-document/xmlsearchtool.md): The `XMLSearchTool` is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a XML file.
- [TXT RAG Search](https://docs.crewai.com/v1.15.28/en/tools/file-document/txtsearchtool.md): The `TXTSearchTool` is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a text file.
- [JSON RAG Search](https://docs.crewai.com/v1.15.28/en/tools/file-document/jsonsearchtool.md): The `JSONSearchTool` is designed to search JSON files and return the most relevant results.
- [CSV RAG Search](https://docs.crewai.com/v1.15.28/en/tools/file-document/csvsearchtool.md): The `CSVSearchTool` is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within a CSV file's content.
- [Directory RAG Search](https://docs.crewai.com/v1.15.28/en/tools/file-document/directorysearchtool.md): The `DirectorySearchTool` is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within a directory's content.
- [Directory Read](https://docs.crewai.com/v1.15.28/en/tools/file-document/directoryreadtool.md): The `DirectoryReadTool` is a powerful utility designed to provide a comprehensive listing of directory contents.
- [OCR Tool](https://docs.crewai.com/v1.15.28/en/tools/file-document/ocrtool.md): The `OCRTool` extracts text from local images or image URLs using an LLM with vision.
- [PDF Text Writing Tool](https://docs.crewai.com/v1.15.28/en/tools/file-document/pdf-text-writing-tool.md): The `PDFTextWritingTool` writes text to specific positions in a PDF, supporting custom fonts.
- [Overview](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/overview.md): Extract data from websites and automate browser interactions with powerful scraping tools
- [Scrape Website](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/scrapewebsitetool.md): The `ScrapeWebsiteTool` is designed to extract and read the content of a specified website.
- [Scrape Element From Website Tool](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/scrapeelementfromwebsitetool.md): The `ScrapeElementFromWebsiteTool` enables CrewAI agents to extract specific elements from websites using CSS selectors.
- [Scrapfly Scrape Website Tool](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/scrapflyscrapetool.md): The `ScrapflyScrapeWebsiteTool` leverages Scrapfly's web scraping API to extract content from websites in various formats.
- [Selenium Scraper](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/seleniumscrapingtool.md): The `SeleniumScrapingTool` is designed to extract and read the content of a specified website using Selenium.
- [Scrapegraph Scrape Tool](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/scrapegraphscrapetool.md): The `ScrapegraphScrapeTool` leverages Scrapegraph AI's SmartScraper API to intelligently extract content from websites.
- [Spider Scraper](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/spidertool.md): The `SpiderTool` is designed to extract and read the content of a specified website using Spider.
- [Browserbase Web Loader](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/browserbaseloadtool.md): Browserbase is a developer platform to reliably run, manage, and monitor headless browsers.
- [Hyperbrowser Load Tool](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/hyperbrowserloadtool.md): The `HyperbrowserLoadTool` enables web scraping and crawling using Hyperbrowser.
- [Stagehand Tool](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/stagehandtool.md): Web automation tool that integrates Stagehand with CrewAI for browser interaction and automation
- [Firecrawl Crawl Website](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/firecrawlcrawlwebsitetool.md): The `FirecrawlCrawlWebsiteTool` is designed to crawl and convert websites into clean markdown or structured data.
- [Firecrawl Scrape Website](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/firecrawlscrapewebsitetool.md): The `FirecrawlScrapeWebsiteTool` is designed to scrape websites and convert them into clean markdown or structured data.
- [Oxylabs Scrapers](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/oxylabsscraperstool.md): Oxylabs Scrapers allow to easily access the information from the respective sources. Please see the list of available sources below:   - `Amazon Product`   - `Amazon Search`   - `Google Search`   - `Universal`
- [Bright Data Tools](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/brightdata-tools.md): Bright Data integrations for SERP search, Web Unlocker scraping, and Dataset API.
- [You.com Content Extraction Tool](https://docs.crewai.com/v1.15.28/en/tools/web-scraping/youai-contents.md): Extract full page content from URLs in markdown, HTML, or metadata format via You.com's remote MCP server.
- [Overview](https://docs.crewai.com/v1.15.28/en/tools/search-research/overview.md): Perform web searches, find repositories, and research information across the internet
- [Google Serper Search](https://docs.crewai.com/v1.15.28/en/tools/search-research/serperdevtool.md): The `SerperDevTool` is designed to search the internet and return the most relevant results.
- [Brave Search Tools](https://docs.crewai.com/v1.15.28/en/tools/search-research/bravesearchtool.md): A suite of tools for querying the Brave Search API — covering web, news, image, and video search.
- [Exa Search Tool](https://docs.crewai.com/v1.15.28/en/tools/search-research/exasearchtool.md): Search the web with Exa, the fastest and most accurate web search API. Get token-efficient highlights and full page content.
- [Linkup Search Tool](htt

Measured from the saved file

Linked document

UTF-8 text size
38.0 KB38950 bytes
Token count
9970o200k_base encoding
Markdown links
225213 distinct URLs
Fenced code blocks
0236 lines in the file

Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.

Project H1
CrewAI

Context architecture

How the content is divided

3 H2 sections organize 225 parsed Markdown links. 199 links point to .md or .markdown paths; 22 link occurrences use another hostname. Linked destinations have not been recursively validated.

H2 sectionLinksUTF-8 bytesTokens
DocsLine 3200374449522
OpenAPI SpecsLine 2054328103
OptionalLine 212 · Optional211131333

Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.

Embedded material

Code, installation and API examples

Fenced blocks
0 closed
Declared languages
No fenced blocks detected
Package-install commands
0 detected in fenced or inline code
Authentication examples
0 fenced lines match API-key, Authorization, Bearer, OAuth or access-token patterns
HTTP request examples
0 fenced lines match request-method patterns
Authentication links
0 links have authentication-related labels

Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.

Publisher prioritization

The Optional section

1 H2 section named “Optional” contain 21 parsed links. 204 links sit outside those sections. That puts 9.3% of the file’s parsed links under Optional.

The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.

Machine-readable routes

MCP references and configuration text

MCP-related text was detected in the captured file. 7 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.

These are text and link observations. No MCP server connection, authentication or tool call was tested.

Index and bundle

llms-full.txt companion

Verified text companion

Text companion verified

https://docs.crewai.com/llms-full.txt ↗
Discovery
Conventional sibling path checked
HTTP response
200 · text/plain; charset=utf-8
Text size
1.8 MB · 1870834 bytes (measured)
Token count
436822 o200k_base tokens
Retrieval scope
Complete body retrieved

A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.

Change evidence

What can be said about freshness

This capture establishes a baseline. Update frequency cannot be determined from one observation.

Linked release and migration material

4 links have release, changelog, deprecation or migration terms in their labels or paths. These provide places to investigate product changes separately.

File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.

Capture identity and measurement method
Requested endpoint
https://docs.crewai.com/llms.txt
Final endpoint
https://docs.crewai.com/llms.txt
HTTP status
200
Content type
text/plain; charset=utf-8
Text retrieval
Firecrawl literal text capture
Tokenizer
tiktoken 0.14.0 · o200k_base
SHA-256 of saved UTF-8 text
48c4f450eaa2e5add303105da7c99d77ab08da94df1ecdd479e85b92a576a5fd

Counts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.

Related tools and resources

Contact Jon