Skip to main content
Glama
memstate-ai

Memstate AI - Agent Memory System

Official

memstate_remember

Save markdown, text, or task summaries to automatically create structured memories with keypath extraction, organization, and versioning for AI agents.

Instructions

Save markdown, task summaries, or any text. Server extracts keypaths and creates structured memories automatically. This is the PREFERRED way to save information.

USE THIS WHEN: Saving task summaries, meeting notes, docs, or any text with multiple facts. The server handles organization, conflict detection, and versioning. NOT FOR: Setting one specific keypath to a short value (e.g. config.port = "8080") — use memstate_set for that.

memstate_remember(project_id="myapp", content="## Task Summary\n- Added OAuth\n- Files: auth.go, middleware.go", source="agent") memstate_remember(project_id="myapp", content="Architecture decision: migrated to JWT tokens for session management")

Content limit: 100,000 chars. Processing is async (~15-18s); returns job_id immediately.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_idYesRequired. Project to store in (e.g. 'myapp'). Auto-creates if new.
contentYesMarkdown or text to remember (max 100,000 chars). Server extracts keypaths and creates structured memories automatically.
sourceNoSource type: agent, readme, docs, meeting, code
contextNoOptional hint to guide keypath extraction

Implementation Reference

  • The memstate_remember tool is dynamically proxied by the MCP server, so its execution is handled by a generic tool call handler that forwards the request to the remote Memstate MCP server.
    server.setRequestHandler(CallToolRequestSchema, async (request) => {
      return await remote.callTool({
        name: request.params.name,
        arguments: request.params.arguments,
      });
    });

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/memstate-ai/memstate-mcp'

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