Skip to main content
Glama

save_memory

Store developer knowledge like facts, preferences, and decisions to persist across coding sessions and future conversations.

Instructions

Store a developer memory (fact, preference, decision, architecture detail). Memories persist across all Claude Code sessions and are available in future conversations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contentYesThe fact to remember (complete sentence)
memory_typeNoType: identity, preference, architecture, decision, bug, dependency, pattern, context. Custom types also accepted for non-developer domains.context
categoryNoCategory: frontend, backend, database, devops, testing, security, performance, tooling, api, general. Custom categories also accepted for non-developer domains.general
subjectNoWhat this is about, e.g. "auth_system", "react_version", "tab_width"
importanceNo1-10 (10 = core architecture, 1 = trivial)
scopeNoglobal = applies everywhere, project = specific to this codebase, team = shared with team membersproject
team_idNoTeam ID (required when scope is "team"). The memory will be shared with all team members.
tagsNoOptional tags for grouping/threading memories (max 5 tags, each max 30 chars). E.g., ["marketing-campaign", "feb-2026"]
ttlNoSet an expiration time. Use for temporary context like current task status. Format: "24h", "7d", "30d". Memory auto-archives after expiry.

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