Showing the first 18000 characters. Load the complete file to read the remainder.
# Redpanda Documentation
---
title: Redpanda Documentation
latest-operator-version: v26.2.4
latest-console-tag: v3.13.0
latest-connect-version: 4.114.0
latest-redpanda-tag: v26.2.5
docname: llms
page-component-name: home
page-version: master
page-component-version: master
page-component-title: Home
page-relative-src-path: llms.adoc
page-edit-url: https://github.com/redpanda-data/docs-site/edit/HEAD/home/modules/ROOT/pages/llms.adoc
page-git-created-date: "2026-03-05"
page-git-modified-date: "2026-09-10"
---
> **Redpanda** is a high-performance streaming data platform and Agentic Data Plane that is fully compatible with the Apache Kafka® API. It enables real-time data streaming, event-driven architectures, and data pipelines with simple single-binary deployment and sub-millisecond latency. The Agentic Data Plane provides enterprise-grade governance and observability for AI agents, including audit trails, compliance controls, and visibility into agent behavior. Available as self-managed software or as a fully-managed cloud service.
## [](#discovery)Discovery
**For AI agents and LLMs:** This documentation is optimized for AI consumption. If you’re an AI agent trying to help with Redpanda, start here.
### [](#find-redpanda-documentation)Find Redpanda documentation
**Primary discovery methods:**
1. **This file**: `https://docs.redpanda.com/llms.txt` - You’re reading it! This follows the llms.txt standard and provides a curated overview with links to comprehensive resources.
2. **Sitemap**: `[https://docs.redpanda.com/sitemap.md](https://docs.redpanda.com/sitemap.md)` - Contains all documentation pages including this file and all exports. The sitemap index includes `[https://docs.redpanda.com/sitemap-llms.md](https://docs.redpanda.com/sitemap-llms.md)` with all AI-optimized exports.
3. **MCP server**: [https://docs.redpanda.com/home/how-to-use-these-docs.md](https://docs.redpanda.com/home/how-to-use-these-docs.md) - For Claude Code and MCP-compatible agents, this provides interactive documentation tools.
### [](#static-documentation-exports)Static documentation exports
**For agents without MCP support**, we provide comprehensive static exports:
- **[https://docs.redpanda.com/llms-full.txt](https://docs.redpanda.com/llms-full.txt)**: Every component in one file, using the latest version of each. Older versions are not included in any export; to read one, request the individual page instead (replace `.html` with `.md` in its URL).
- **Component-specific exports**: Focused documentation for individual products. Smaller and cheaper to index than the full export:
- **[https://docs.redpanda.com/streaming-full.txt](https://docs.redpanda.com/streaming-full.txt)**: Redpanda Streaming documentation
- **[https://docs.redpanda.com/cloud-data-platform-full.txt](https://docs.redpanda.com/cloud-data-platform-full.txt)**: Redpanda Cloud documentation
- **[https://docs.redpanda.com/connect-full.txt](https://docs.redpanda.com/connect-full.txt)**: Redpanda Connect documentation
- **[https://docs.redpanda.com/agentic-data-plane-full.txt](https://docs.redpanda.com/agentic-data-plane-full.txt)**: Agentic Data Plane documentation
- **[https://docs.redpanda.com/labs-full.txt](https://docs.redpanda.com/labs-full.txt)**: Labs and tutorials
- **[https://docs.redpanda.com/home-full.txt](https://docs.redpanda.com/home-full.txt)**: Documentation home and cross-product guidance
> 📝 **NOTE**
>
> The API reference is linked from these exports but its content is not included, because it is generated from OpenAPI specs and hosted separately. For endpoint-level detail, follow the `[https://docs.redpanda.com/api/](https://docs.redpanda.com/api/)` links.
### [](#individual-markdown-pages)Individual Markdown pages
**Every HTML page has a markdown equivalent:**
1. **Direct access**: Replace `.html` with `.md` in any URL
- Example: `[https://docs.redpanda.com/streaming/current/get-started.html](https://docs.redpanda.com/streaming/current/get-started.html)` → `[https://docs.redpanda.com/streaming/current/get-started.md](https://docs.redpanda.com/streaming/current/get-started.md)`
2. **Content negotiation**: Request any URL with `Accept: text/markdown` header
**Markdown features:**
- YAML frontmatter with page metadata (title, description, categories, topic type, personas)
- Git dates (accurate created/modified dates from commit history)
- GitHub-Flavored Markdown format
## [](#overview)Overview
Redpanda docs serve both new and experienced users, offering detailed technical resources across Redpanda’s product suite.
- **[Redpanda Streaming](https://docs.redpanda.com/streaming.md):** Deploy and manage Redpanda in your environment for ultimate control, high performance, and fault tolerance with Kafka compatibility and advanced enterprise features like Tiered Storage.
- **[Redpanda Cloud](https://docs.redpanda.com/cloud-data-platform.md):** Simplify streaming with a fully-managed service: Serverless, Bring Your Own Cloud (BYOC), or Dedicated. Serverless is the fastest and easiest way to start data streaming. Choose BYOC for full data sovereignty.
- **[Redpanda Connect](https://docs.redpanda.com/connect.md):** Effortlessly integrate data across systems with hundreds of prebuilt connectors, change data capture (CDC) capabilities, and YAML-configurable workflows. Available as a standalone solution or as part of Redpanda Streaming, Redpanda Connect empowers organizations to build scalable, high-performance data pipelines with minimal complexity.
- **[Redpanda Agentic Data Plane](https://docs.redpanda.com/agentic-data-plane/get-started/adp-overview.md):** Enterprise-grade infrastructure for building, deploying, and governing AI agents at scale. Provides Model Context Protocol (MCP) integration, declarative agent configuration, and compliance-grade audit trails for AI agents that need direct access to databases, queues, and business systems.
- **[Redpanda Console](https://docs.redpanda.com/streaming/current/console.md):** Streamline operations with an intuitive Kafka UI for managing topics, partitions, and consumer groups, providing visibility and control over your data pipeline.
## [](#core-documentation)Core documentation
- [Get started](https://docs.redpanda.com/streaming/current/get-started/quickstarts.md): Fast-track your journey with Redpanda Streaming by deploying a complete example in Docker.
- [Redpanda concepts](https://docs.redpanda.com/streaming/current/get-started/architecture.md): Deep-dive into key concepts like Tiered Storage, partitions, replication, and data streaming architecture.
## [](#deployment-guides)Deployment guides
- [Redpanda Streaming](https://docs.redpanda.com/streaming/current/deploy.md): Install and configure Redpanda and Redpanda Console in self-hosted environments, including production best practices. Choose from Linux (bare-metal) or Kubernetes deployment instructions.
- [Redpanda Cloud](https://docs.redpanda.com/cloud-data-platform/get-started/cluster-types.md): Guides for using Redpanda Cloud across Serverless, BYOC, and Dedicated options.
- [Redpanda Connect](https://docs.redpanda.com/connect.md): Standalone documentation for deploying and managing Redpanda Connect, with or without Redpanda.
## [](#redpanda-cli)Redpanda CLI
Learn about `rpk`, the comprehensive command-line interface tool for managing Redpanda clusters.
- [rpk documentation for Redpanda Streaming](https://docs.redpanda.com/streaming/current/reference/rpk/rpk-commands.md)
- [rpk documentation for Redpanda Cloud](https://docs.redpanda.com/cloud-data-platform/reference/rpk/rpk-commands.md)
## [](#redpanda-console)Redpanda Console
- [About Redpanda Console](https://docs.redpanda.com/streaming/current/console.md): Learn about Redpanda’s Kafka UI for managing topics, partitions, and consumer groups.
- [Configure Redpanda Console](https://docs.redpanda.com/streaming/current/manage/console.md): Learn how to configure Redpanda Console for your needs.
## [](#ai-agents-and-agentic-data-plane)AI agents and Agentic Data Plane
Build and deploy production-ready AI agents with enterprise governance and compliance.
### [](#get-started)Get started
- [Agentic Data Plane Overview](https://docs.redpanda.com/agentic-data-plane/get-started/adp-overview.md): Enterprise infrastructure for AI agents with built-in governance, observability, and compliance.
- [Quickstart for Administrators](https://docs.redpanda.com/agentic-data-plane/get-started/adp-quickstart.md): Set up Agentic Data Plane for your organization. Configure an LLM provider, verify it, and hand off to your agent builders.
- [Quickstart for Agent Builders](https://docs.redpanda.com/agentic-data-plane/get-started/agent-builder-quickstart.md): Sign in, explore the agents your organization runs, then build and test your own agent backed by MCP tools.
### [](#build-agents-and-connect-tools)Build agents and connect tools
- [How Agents Work](https://docs.redpanda.com/agentic-data-plane/connect/agents-overview.md): Build agents declaratively by selecting an LLM, writing a system prompt, and attaching prebuilt tools and integrations instead of writing custom agent code.
- [How MCP Servers Work](https://docs.redpanda.com/agentic-data-plane/connect/mcp-overview.md): Connect AI agents to your databases, APIs, and business systems through managed MCP servers Redpanda hosts, or self-managed servers you register.
- [Plug in an App, Database, or Tool](https://docs.redpanda.com/agentic-data-plane/connect/managed/managed-catalog.md): Every managed MCP server type Redpanda hosts, grouped by category, with links to setup guides.
- [Connect Remote MCP Clients](https://docs.redpanda.com/agentic-data-plane/connect/remote-mcp-clients.md): Connect external MCP clients to MCP servers in AI Gateway using client metadata documents, dynamic client registration, or manual registration.
### [](#ai-gateway-and-llm-providers)AI Gateway and LLM providers
- [How AI Gateway Works](https://docs.redpanda.com/agentic-data-plane/gateway/overview.md): The managed proxy for LLM APIs in Agentic Data Plane. Each provider gets a Redpanda-hosted URL with secrets, authentication, and observability.
- [Configure an LLM Provider](https://docs.redpanda.com/agentic-data-plane/gateway/configure-provider.md): Create an LLM provider to proxy requests to OpenAI, Anthropic, Google AI, AWS Bedrock, or any OpenAI-compatible endpoint.
- [Set Up AWS Bedrock as an LLM Provider](https://docs.redpanda.com/agentic-data-plane/gateway/bedrock-setup.md): Create the IAM user, policy, and access keys AI Gateway needs to invoke Amazon Bedrock models, then register the provider.
- [Connect Your App to AI Gateway](https://docs.redpanda.com/agentic-data-plane/gateway/connect-agent.md): Point your app or AI agent at an AI Gateway proxy URL, authenticate with rpk ai or OIDC client credentials, and send requests with your SDK.
- [Run Claude Code and Codex through AI Gateway](https://docs.redpanda.com/agentic-data-plane/connect/coding-agents.md): Launch Claude Code or Codex with rpk ai run, routing model traffic through a managed, enterprise-passthrough, or AWS Bedrock provider.
### [](#govern-and-observe)Govern and observe
- [Set Up Guardrails](https://docs.redpanda.com/agentic-data-plane/control/guardrails.md): Understand how guardrails work, create them, review blocked requests, and look up the available policies.
- [Manage Access Policies](https://docs.redpanda.com/agentic-data-plane/control/access-policies.md): Create Cedar-based access policies that permit or forbid specific actions, with conditions over resource tags and ownership.
- [Set Up Budgets](https://docs.redpanda.com/agentic-data-plane/control/budgets.md): Cap LLM spend with per-agent budgets and see what Agentic Data Plane records automatically.
- [Analyze Cost and Usage](https://docs.redpanda.com/agentic-data-plane/control/cost-usage.md): Break down LLM spend, requests, and tokens by provider, model, agent, user, or tag. Compare periods and export CSV.
- [Review the Audit Log](https://docs.redpanda.com/agentic-data-plane/monitor/audit-log.md): Review authorization decisions, filter them, and see who acted on which resource and whether the request was allowed.
- [See What Your Agent Did](https://docs.redpanda.com/agentic-data-plane/monitor/transcripts.md): Open a transcript, read the conversation turn by turn, and investigate errors and performance.
### [](#command-line-and-gitops)Command line and GitOps
- [Use the Agentic Data Plane CLI](https://docs.redpanda.com/agentic-data-plane/cli.md): Manage Agentic Data Plane resources from the terminal with rpk ai. Install the CLI, connect to an AI Gateway, and script providers, servers, and agents.
- [Manage Resources with GitOps](https://docs.redpanda.com/agentic-data-plane/cli/gitops.md): Keep Agentic Data Plane resources in Git and reconcile them with rpk ai apply and diff for declarative create-or-update, drift detection, and CI gating.
## [](#api-references)API references
- [Admin API](https://docs.redpanda.com/api/doc/admin.md): Manage and monitor Redpanda clusters using this REST API, including operations for configuration, partitions, and node health.
- [Schema Registry API](https://docs.redpanda.com/api/doc/schema-registry.md): Use Redpanda’s Kafka-compatible schema registry for managing and evolving schemas in your data streams.
- [HTTP Proxy API](https://docs.redpanda.com/api/doc/http-proxy.md): Simplify interactions with Kafka topics and partitions with Redpanda’s HTTP Proxy API, enabling easier data production and consumption over HTTP.
- [Cloud API](https://docs.redpanda.com/api/doc/cloud-controlplane.md): Access and manage Redpanda Cloud resources programmatically, including provisioning clusters, monitoring usage, and configuring deployments.
## [](#troubleshooting)Troubleshooting
- [Troubleshooting guide](https://docs.redpanda.com/streaming/current/troubleshoot.md): Resolve common issues with installation, configuration, and performance.
- [Debug bundles](https://docs.redpanda.com/streaming/current/troubleshoot/debug-bundle.md): Generate and analyze debug bundles for diagnosing cluster issues.
## Page indexes
Each file below lists pages as links to their markdown versions. Start with the latest version of a product unless you need a specific older version.
### Agentic Data Plane
- [Agentic Data Plane](https://docs.redpanda.com/agentic-data-plane/llms.txt): 92 pages
- [Agentic Data Plane: reference](https://docs.redpanda.com/agentic-data-plane/reference/llms.txt): 147 pages
### Cloud
- [Cloud: develop/connect/components](https://docs.redpanda.com/cloud-data-platform/develop/connect/components/llms.txt): 175 pages
- [Cloud: develop/connect/components/processors](https://docs.redpanda.com/cloud-data-platform/develop/connect/components/processors/llms.txt): 84 pages
- [Cloud: develop/connect](https://docs.redpanda.com/cloud-data-platform/develop/connect/llms.txt): 35 pages
- [Cloud: develop](https://docs.redpanda.com/cloud-data-platform/develop/llms.txt): 49 pages
- [Cloud](https://docs.redpanda.com/cloud-data-platform/llms.txt): 184 pages
- [Cloud: reference](https://docs.redpanda.com/cloud-data-platform/reference/llms.txt): 166 pages
- [Cloud: reference/sql](https://docs.redpanda.com/cloud-data-platform/reference/sql/llms.txt): 97 pages
- [Cloud: reference/sql/sql-functions](https://docs.redpanda.com/cloud-data-platform/reference/sql/sql-functions/llms.txt): 170 pages
### Connect
- [Connect: components](https://docs.redpanda.com/connect/components/llms.txt): 231 pages
- [Connect: components/processors](https://docs.redpanda.com/connect/components/processors/llms.txt): 98 pages
- [Connect](https://docs.redpanda.com/connect/llms.txt): 85 pages
### Home
- [Home](https://docs.redpanda.com/home/llms.txt): 3 pages
### Labs
- [Labs](https://docs.redpanda.com/labs/llms.txt): 33 pages
### Streaming
- [Streaming 26.2](https://docs.redpanda.com/streaming/current/llms.txt): 151 pages
- [Streaming 26.2: manage](https://docs.redpanda.com/streaming/current/manage/llms.txt): 139 pages
- [Streaming 26.2: reference](https://docs.redpanda.com/streaming/current/reference/llms.txt): 27 pages
- [Streaming 26.2: reference/rpk](https://docs.redpanda.com/streaming/current/reference/rpk/llms.txt): 170 pages
- [Streaming 26.2: reference/rpk/rpk-cluster](https://docs.redpanda.com/streaming/current/reference/rpk/rpk-cluster/llms.txt): 67 pages
Older versions:
- [Streaming 26.1](https://docs.redpanda.com/streaming/26.1/llms.txt): 148 pages
- [Streaming 26.1: manage](https://docs.redpanda.com/streaming/26.1/manage/llms.txt): 130 pages
- [Streaming 26.1: reference](https://docs.redpanda.com/streaming/26.1/reference/llms.txt): 26 pages
- [Streaming 26.1: reference/rpk](https://docs.redpanda.com/streaming/26.1/reference/rpk/llms.txt): 169 pages
- [Streaming 26.1: reference/rpk/rpk-cluster](https://docs.redpanda.com/streaming/26.1/reference/rpk/rpk-cluster/llms.txt): 57 pages
- [Streaming 25.3](https://docs.redpanda.com/streaming/25.3/llms.txt): 143 pages
- [Streaming 25.3: manage](https://docs.redpanda.com/streaming/25.3/manage/llms.txt): 117 pages
- [Streaming 25.3: reference](https://docs.redpanda.com/streaming/25.3/reference/llms.txt): 238 pages
- [Streaming 25.2](https://docs.redpanda.com/streaming/25.2/llms.txt): 142 pages
- [Streaming 25.2: manage](https://docs.redpanda.com/streaming/25.2/manage/llms.txt): 102 pages
- [Streaming 25.2: reference](https://docs.redpanda.com/streaming/25.2/reference/llms.txt): 226 pages
- [Streaming 25.1](https://docs.redpanda.com/streaming/25.1/llms.txt): 133 pages
- [Streaming 25.1: manage](https://docs.redpanda.com/streaming/25.1/manage/llms.txt): 98 pages
- [Streaming 25.1: reference](https://docs.redpanda.com/streaming/25.1/reference/llms.txt): 222 pages
- [St
Measured from the saved file
Linked document
UTF-8 text size
23.3 KB23811 bytes
Token count
6061o200k_base encoding
Markdown links
167160 distinct URLs
Fenced code blocks
0360 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
Redpanda Documentation
Opening blockquote
**Redpanda** is a high-performance streaming data platform and Agentic Data Plane that is fully compatible with the Apache Kafka® API. It enables real-time data streaming, event-driven architectures, and data pipelines with simple single-binary deployment and sub-millisecond latency. The Agentic Data Plane provides enterprise-grade governance and observability for AI agents, including audit trails, compliance controls, and visibility into agent behavior. Available as self-managed software or as a fully-managed cloud service.
Context architecture
How the content is divided
11 H2 sections organize 167 parsed Markdown links. 100 links point to .md or .markdown paths; 0 link occurrences use another hostname. Linked destinations have not been recursively validated.
H2 section
Links
UTF-8 bytes
Tokens
[](#discovery)DiscoveryLine 24
12
3431
841
[](#overview)OverviewLine 86
6
1729
360
[](#core-documentation)Core documentationLine 101
3
391
89
[](#deployment-guides)Deployment guidesLine 108
4
610
139
[](#redpanda-cli)Redpanda CLILine 117
3
344
83
[](#redpanda-console)Redpanda ConsoleLine 126
3
331
80
[](#ai-agents-and-agentic-data-plane)AI agents and Agentic Data PlaneLine 133
26
4968
1160
[](#api-references)API referencesLine 192
5
815
171
[](#troubleshooting)TroubleshootingLine 203
3
327
71
Page indexesLine 209
43
4465
1401
Complete documentation indexLine 278
59
4937
1311
Nested indexes
43 distinct links point to other llms.txt paths. These are routes to more indexes, not proof their contents were included in this file.
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
No H2 section named “Optional” was detected in this file.
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. 2 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.
Bounded prefix inspected; the whole body was not downloaded
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.
File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.
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.