LLM & AI Access

Orcaq documentation is structured for direct consumption by LLMs and AI tools. Whether you're grounding a language model with product context or building an autonomous coding assistant, the resources below give you everything you need.

Quick Access Files

We provide structured txt files at the root of the site specifically formatted for LLM context windows:

File	URL	Description
`llms.txt`	orca-q.com/llms.txt	Curated entry point: product context, core features, supported database matrices, and organized page links.
`llms-full.txt`	orca-q.com/llms-full.txt	Single-file full context: merges core details, canonical links, FAQs, and a complete documentation mapping.
`/docs/llms.txt`	orca-q.com/docs/llms.txt	Sub-index of all individual documentation pages context.
`/blogs/llms.txt`	orca-q.com/blogs/llms.txt	Sub-index of all blog posts context.

Using with AI Tools

ChatGPT, Claude, and Other LLMs

Paste this prompt to load Orcaq context into any LLM:

text

Fetch https://orca-q.com/llms.txt and use it to answer questions about Orcaq.

llms.txt includes all supported database statuses (PostgreSQL native, MySQL/MariaDB/SQLite/OracleDB/Redis in beta), installation instructions, environment tags explanation, and links to all documentation pages.

Cursor, Windsurf, and AI Code Editors

You can reference our structured files directly inside your development workflows:

Cursor: Add https://orca-q.com/llms.txt (or https://orca-q.com/llms-full.txt for deeper context) as a doc source in Settings → Features → Docs
Windsurf: Include the URL in your workspace context
VS Code Copilot: Reference the URL directly in your chat prompt using @url

Programmatic Access

You can fetch the structured files via terminal or script:

bash

# Fetch the curated summary reference
curl https://orca-q.com/llms.txt

# Fetch the full single-file context
curl https://orca-q.com/llms-full.txt

llms.txt Standard

Orcaq follows the llms.txt specification, an emerging open standard that makes documentation natively accessible to AI systems — analogous to robots.txt for search crawlers. The format provides:

Product context — database client details, pricing (free and open source), target audience
Key capabilities — workspace management, strict mode environment tags, ERD tool, AI agent assistant
Supported databases matrix — natively supported vs beta database connectors vs coming soon roadmap
Organized page links — every documentation page and blog post with a one-line description

Best Practices

When using Orcaq docs with AI tools:

Ground with llms.txt first — load it as context before asking database-specific questions
Reference specific pages — for focused queries, link directly to the relevant documentation page (e.g. /docs/connections/overview for connection types, or /docs/features/strict-mode for safety guardrails)
Keep context updated — the documentation is continuously updated. AI tools accessing these URLs will always receive the latest content.