Skip to main content
Glama

memorix_search

Search project memory across IDE sessions to retrieve context from observations, enabling cross-session knowledge retrieval with filtering by type, scope, and status.

Instructions

Search project memory. Returns a compact index (~50-100 tokens/result). Use memorix_detail to fetch full content for specific IDs. Use memorix_timeline to see chronological context. Searches across all observations stored from any IDE session — enabling cross-session and cross-agent context retrieval.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query (natural language or keywords)
limitNoMax results (default: 20)
typeNoFilter by observation type
maxTokensNoToken budget — trim results to fit (0 = unlimited)
scopeNoSearch scope: "project" (default) only searches current project, "global" searches all projectsproject
sinceNoOnly return observations created after this date (ISO 8601 or natural like "2025-01-15")
untilNoOnly return observations created before this date (ISO 8601 or natural like "2025-02-01")
statusNoFilter by memory status. "active" (default) shows current memories, "all" includes resolved/archived.active

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/AVIDS2/memorix'

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