Skip to main content
Glama

remember

Store information in persistent memory for later recall across sessions. Save user preferences, project decisions, important facts, and other data that needs to be remembered over time.

Instructions

Store information in persistent memory for later recall. Use when you learn something that should be remembered across sessions — user preferences, project decisions, important facts, or anything you might need later.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contentYesThe information to remember. Be specific and include context so it's useful when recalled later.
agent_idNoIdentifier for this agent instancedefault
user_idNoUser identifier for user-scoped memories
tagsNoTags for categorizing the memory (e.g., 'preference', 'decision', 'fact')
scopeNoVisibility scope: agent (only this agent), user (all agents for this user), org (all agents in the organization)agent

Implementation Reference

  • The 'remember' tool implementation, defining the schema and the async handler that calls the external API.
    server.tool(
      "remember",
      "Store information in persistent memory for later recall. Use when you learn something that should be remembered across sessions — user preferences, project decisions, important facts, or anything you might need later.",
      {
        content: z
          .string()
          .describe(
            "The information to remember. Be specific and include context so it's useful when recalled later.",
          ),
        agent_id: z
          .string()
          .default("default")
          .describe("Identifier for this agent instance"),
        user_id: z
          .string()
          .optional()
          .describe("User identifier for user-scoped memories"),
        tags: z
          .array(z.string())
          .default([])
          .describe(
            "Tags for categorizing the memory (e.g., 'preference', 'decision', 'fact')",
          ),
        scope: z
          .enum(["agent", "user", "org"])
          .default("agent")
          .describe(
            "Visibility scope: agent (only this agent), user (all agents for this user), org (all agents in the organization)",
          ),
      },
      async ({ content, agent_id, user_id, tags, scope }) => {
        const result = await apiCall("/memories/remember", "POST", {
          agent_id,
          user_id,
          content,
          tags,
          scope,
        });
    
        const memory = (result as { memory: { id: string; created_at: string } })
          .memory;
        return {
          content: [
            {
              type: "text" as const,
              text: `Remembered (id: ${memory.id}, stored at: ${memory.created_at}). This memory will be available in future sessions.`,
            },
          ],
        };
      },
    );
Install Server

Other Tools

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/AlekseiMarchenko/central-intelligence'

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