Skip to content
J·BJon BishopFractional growth marketer

Artificial intelligence · llms.txt file breakdown

CBK AI llms.txt

A directly retrieved Markdown index for CBK AI's documentation, with 13 links across 5 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 ↗

Complete saved Markdown shown below.

# CBK AI

> CBK AI (ChatBotKit) is a platform for building intelligent AI agents that can understand, reason, and take action. Designed for developers building agentic AI with Node.js, serverless environments, and modern JavaScript frameworks.

CBK AI provides a comprehensive suite of tools and SDKs for building sophisticated agentic AI systems. The platform focuses on developer experience with clean APIs, comprehensive documentation, and support for all major AI models and deployment environments including AWS Lambda, Vercel Edge, and Cloudflare Workers.

Key features include:
- Multi-model support with unified interface
- Function calling and tool integration
- Real-time streaming completions
- Lightweight SDK design
- Serverless-optimized architecture
- CBK Relay for standardized AI API access

## Getting Started

- [Sign In](https://console.cbk.ai): No-code agent builder interface
- [Developer Docs](https://docs.cbk.ai): Complete SDK documentation and API references
- [SDK Overview](https://docs.cbk.ai/sdks): Core SDK installation and setup

## Core SDKs

- [@chatbotkit/sdk](https://docs.cbk.ai/sdks/@chatbotkit/sdk): Core API SDK for Node.js and serverless
- [@chatbotkit/agent](https://www.npmjs.com/package/@chatbotkit/agent): Agent SDK for building autonomous agents
- [@chatbotkit/react](https://docs.cbk.ai/sdks/@chatbotkit/react): React hooks and components
- [React Native SDK](https://docs.cbk.ai/react-native-sdk): Streaming and headless hooks for React Native and Expo apps
- [@chatbotkit/next](https://docs.cbk.ai/sdks/@chatbotkit/next): Next.js server and client utilities
- [@chatbotkit/fetch](https://docs.cbk.ai/sdks/@chatbotkit/fetch): Isomorphic fetch implementation

## SDKs for Other Languages and Tooling

- [Go SDK](https://github.com/chatbotkit/go-sdk): Official SDK for Go applications and services (`github.com/chatbotkit/go-sdk`)
- [Python SDK](https://pypi.org/project/chatbotkit/): Official async Python SDK (`pip install chatbotkit`)
- [Terraform Provider](https://registry.terraform.io/providers/chatbotkit/chatbotkit): Provision and manage ChatBotKit resources as infrastructure-as-code
- [CLI](https://www.npmjs.com/package/@chatbotkit/cli): Manage agents and platform resources from the command line

## Optional

- [GitHub](https://github.com/chatbotkit/node-sdk): SDK source code and examples

Measured from the saved file

Linked document

UTF-8 text size
2.3 KB2349 bytes
Token count
559o200k_base encoding
Markdown links
1414 distinct URLs
Fenced code blocks
039 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
CBK AI

Opening blockquote

CBK AI (ChatBotKit) is a platform for building intelligent AI agents that can understand, reason, and take action. Designed for developers building agentic AI with Node.js, serverless environments, and modern JavaScript frameworks.

Context architecture

How the content is divided

4 H2 sections organize 14 parsed Markdown links. 0 links point to .md or .markdown paths; 14 link occurrences use another hostname. Linked destinations have not been recursively validated.

H2 sectionLinksUTF-8 bytesTokens
Getting StartedLine 15323459
Core SDKsLine 216632183
SDKs for Other Languages and ToolingLine 304508119
OptionalLine 37 · Optional18222

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
1 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.

Detected installation lines

Source line 33 · inline

pip install chatbotkit

Publisher prioritization

The Optional section

1 H2 section named “Optional” contain 1 parsed links. 13 links sit outside those sections. That puts 7.1% 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

No MCP or Model Context Protocol term was detected in the captured file. 0 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

Not found at checked URLs

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.

Capture identity and measurement method
Requested endpoint
https://cbk.ai/llms.txt
Final endpoint
https://cbk.ai/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
39f964056e4ef2c00050720e511405f6c87ba9179f806bba3f279569321c2dc3

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