Skip to main content
Glama

add_memory

Store development preferences, decisions, and project facts for automatic retrieval via semantic search in future sessions.

Instructions

Store a memory for future sessions. Memories are persisted as markdown files and automatically retrieved via semantic search when relevant.

Categories:

  • preferences: Coding style, tool preferences, personal workflow choices

  • decisions: Architecture decisions, technology choices, design rationale

  • facts: Project facts, environment info, codebase structure

Examples:

  • Add preference: "Prefers TypeScript strict mode"

  • Add decision: "Chose JWT for authentication because..."

  • Add fact: "API runs on port 3000"

Memories are stored in .memories/ directory and indexed by Auggie for semantic retrieval.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
categoryYesCategory of memory: preferences (coding style), decisions (architecture), or facts (project info)
contentYesThe memory content to store (max 5000 characters)
titleNoOptional title for the memory (useful for decisions)

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Kirachon/context-engine'

If you have feedback or need assistance with the MCP directory API, please join our Discord server