Skip to main content
Glama

recall_memories

Search stored memories using semantic queries to retrieve relevant context from past sessions, with results ranked by relevance, importance, and recency.

Instructions

Search stored memories using semantic search. Returns memories ranked by relevance, importance, and recency. Use this to find relevant context from past sessions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesWhat to search for (natural language)
scopeNoFilter by scopeall
limitNoMax results
memory_typeNoFilter by type
categoryNoFilter by category (e.g., "backend", "frontend", or any custom category)
importance_minNoOnly return memories with importance >= this value
tagNoFilter by tag (e.g., "marketing-campaign")
team_idNoOptional override. Team memories are automatically included for team/enterprise users.
context_typeNoOptional context type that shifts scoring weights. debugging = boost bug/pattern memories, planning = boost architecture/decision, reviewing = boost pattern/preference.
synthesizeNoWhen true and 3+ results are found, returns an AI-synthesized summary combining all memories into a coherent answer.

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/hifriendbot/cogmemai-mcp'

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