Skip to main content
Memories are markdown files that provide persistent context to every conversation in a project. They’re automatically loaded and included in the system prompt, giving the AI assistant relevant background about your codebase, conventions, and preferences.

Context Files

Reliant discovers two context files in your project root: Both files are automatically loaded when present. Their contents are concatenated and included in every conversation.

What to Include

Project Context (reliant.md)

Include information that benefits everyone working on the project:

Personal Context (reliant.local.md)

Include your personal preferences and local setup details:

Auto-Discovery

Reliant searches for context files in:
  1. Your project root directory
  2. Parent directories (for monorepos)
Files are discovered in this order and concatenated:
  1. reliant.md from root
  2. reliant.local.md from root
[!TIP] Monorepo tip: Place a reliant.md in your monorepo root with shared context, and additional reliant.md files in each package for package-specific context.

Best Practices

Keep it concise — Context files are included in every conversation. Large files consume tokens without proportional benefit. Update regularly — As your project evolves, keep context files current. Outdated information is worse than no information. Separate concerns — Put team knowledge in reliant.md, personal preferences in reliant.local.md. Use structure — Headings and bullet points are easier to scan than prose. Avoid secrets — Never put API keys, passwords, or sensitive data in context files.

Global Context

You can also add global context that applies to all projects. Create a reliant.md file in your global config directory:
This is useful for personal preferences that should apply everywhere:
Global context is loaded before project context, so project-specific context can override global defaults.