AI Assistant Guide

This guide helps you, the AI assistant, use Basic Memory tools effectively when working with users. It covers reading, writing, and navigating knowledge through the Model Context Protocol (MCP).

​

Quick Reference

​

Overview

Basic Memory allows you and users to record context in local Markdown files, building a rich knowledge base through natural conversations. The system automatically creates a semantic knowledge graph from simple text patterns.

• Local-First: All data is stored in plain text files on the user’s computer
• Real-Time: Users see content updates immediately
• Bi-Directional: Both you and users can read and edit notes
• Semantic: Simple patterns create a structured knowledge graph
• Persistent: Knowledge persists across sessions and conversations

​

The Importance of the Knowledge Graph

Basic Memory’s value comes from connections between notes, not just the notes themselves. When writing notes, your primary goal should be creating a rich, interconnected knowledge graph.

When creating content, focus on:

1. Increasing Semantic Density: Add multiple observations and relations to each note
2. Using Accurate References: Aim to reference existing entities by their exact titles
3. Creating Forward References: Feel free to reference entities that don’t exist yet - Basic Memory will resolve these when they’re created later
4. Creating Bidirectional Links: When appropriate, connect entities from both directions
5. Using Meaningful Categories: Add semantic context with appropriate observation categories
6. Choosing Precise Relations: Use specific relation types that convey meaning

​

Core Tools Reference

​

Essential Content Management

Writing knowledge (most important tool):

write_note(
    title="Search Design",
    content="# Search Design\n...",
    folder="specs",                     # Optional
    tags=["search", "design"],          # v0.13.0: now searchable!
    project="work-notes"                # v0.13.0: target specific project
)

Reading knowledge:

read_note("Search Design")              # By title
read_note("specs/search-design")        # By path
read_note("memory://specs/search")      # By memory URL

Viewing notes as formatted artifacts (Claude Desktop):

view_note("Search Design")              # Creates readable artifact
view_note("specs/search-design")        # By permalink
view_note("memory://specs/search")      # By memory URL

Incremental editing (v0.13.0):

edit_note(
    identifier="Search Design",         # Must be EXACT title/permalink (strict matching)
    operation="append",                 # append, prepend, find_replace, replace_section
    content="\n## New Section\nContent here..."
)

File organization (v0.13.0):

move_note(
    identifier="Old Note",              # Must be EXACT title/permalink (strict matching)
    destination="archive/old-note.md"   # Folders created automatically
)

​

Project Management (v0.13.0)

list_projects()                         # Show available projects
switch_project("work-notes")            # Change active project
get_current_project()                   # Current project info

​

Search & Discovery

search_notes("authentication system")   # v0.13.0: includes frontmatter tags
build_context("memory://specs/search")  # Follow knowledge graph connections
recent_activity(timeframe="1 week")     # Check what's been updated

​

memory:// URLs Explained

Basic Memory uses a special URL format to reference entities in the knowledge graph:

memory://title

​

Semantic Markdown Format

Knowledge is encoded in standard markdown using simple patterns:

- [category] This is an observation #tag1 #tag2 (optional context)

- [category] This is an observation #tag1 #tag2 (optional context)

- relation_type [[Target Entity]] (optional context)

Common Categories & Relation Types:

• Categories: [idea], [decision], [question], [fact], [requirement], [technique], [recipe], [preference]
• Relations: relates_to, implements, requires, extends, part_of, pairs_with, inspired_by, originated_from

​

When to Record Context

Protocol for recording context:

1. Identify valuable information in the conversation
2. Ask the user: “Would you like me to record our discussion about [topic] in Basic Memory?”
3. If they agree, use write_note to capture the information
4. If they decline, continue without recording
5. Let the user know when information has been recorded: “I’ve saved our discussion about [topic] to Basic Memory.”

​

Understanding User Interactions

Users will interact with Basic Memory in patterns like:

​

Key Things to Remember

​

Common Knowledge Patterns

​

Capturing Decisions

---
title: Coffee Brewing Methods
tags: [coffee, brewing, pour-over, techniques]  # v0.13.0: Now searchable!
---

# Coffee Brewing Methods

## Context
I've experimented with various brewing methods including French press, pour over, and espresso.

## Decision
Pour over is my preferred method for light to medium roasts because it highlights subtle flavors and offers more control over the extraction.

## Observations
- [technique] Blooming the coffee grounds for 30 seconds improves extraction #brewing
- [preference] Water temperature between 195-205°F works best #temperature
- [equipment] Gooseneck kettle provides better control of water flow #tools
- [timing] Total brew time of 3-4 minutes produces optimal extraction #process

## Relations
- pairs_with [[Light Roast Beans]]
- contrasts_with [[French Press Method]]
- requires [[Proper Grinding Technique]]
- part_of [[Morning Coffee Routine]]

​

Recording Project Structure

# Garden Planning

## Overview
This document outlines the garden layout and planting strategy for this season.

## Observations
- [structure] Raised beds in south corner for sun exposure #layout
- [structure] Drip irrigation system installed for efficiency #watering
- [pattern] Companion planting used to deter pests naturally #technique

## Relations
- contains [[Vegetable Section]]
- contains [[Herb Garden]]
- implements [[Organic Gardening Principles]]

​

Technical Discussions

# Recipe Improvement Discussion

## Key Points
Discussed strategies for improving the chocolate chip cookie recipe.

## Observations
- [issue] Cookies spread too thin when baked at 350°F #texture
- [solution] Chilling dough for 24 hours improves flavor and reduces spreading #technique
- [decision] Will use brown butter instead of regular butter #flavor

## Relations
- improves [[Basic Cookie Recipe]]
- inspired_by [[Bakery-Style Cookies]]
- pairs_with [[Homemade Ice Cream]]

​

v0.13.0 Workflow Examples

​

Multi-Project Conversations

User: “I need to update my work documentation and also add a personal recipe note.”

Workflow:

1. list_projects() - Check available projects
2. write_note(title="Sprint Planning", project="work-notes") - Work content
3. write_note(title="Weekend Recipes", project="personal") - Personal content

​

Incremental Note Building

User: “Add a troubleshooting section to my setup guide.”

Workflow:

1. edit_note(identifier="Setup Guide", operation="append", content="\n## Troubleshooting\n...")

User: “Update the authentication section in my API docs.”

Workflow:

1. edit_note(identifier="API Documentation", operation="replace_section", section="## Authentication")

​

Smart File Organization

User: “My notes are getting messy in the main folder.”

Workflow:

1. move_note("Old Meeting Notes", "archive/2024/old-meetings.md")
2. move_note("Project Notes", "projects/client-work/notes.md")

​

Creating Effective Relations

When creating relations:

1. Reference existing entities by their exact title: [[Exact Title]]
2. Create forward references to entities that don’t exist yet - they’ll be linked automatically when created
3. Search first to find existing entities to reference
4. Use meaningful relation types: implements, requires, part_of vs generic relates_to

Example workflow:

1. search_notes("travel") to find existing travel-related notes
2. Reference found entities: - part_of [[Japan Travel Guide]]
3. Add forward references: - located_in [[Tokyo]] (even if Tokyo note doesn’t exist yet)

​

Common Issues & Solutions

​

Best Practices

​

1. Proactively Record Context

​

2. Create a Rich Semantic Graph

​

3. Structure Content Thoughtfully

​

4. Navigate Knowledge Effectively

• Start with specific searches
• Follow relation paths
• Combine information from multiple sources
• Verify information is current
• Build a complete picture before responding

​

5. Help Users Maintain Their Knowledge

Built with ♥️ by Basic Machines