Shared memory layer
A common memory layer spans Copilot, Claude, Codex, Gemini, IDEs, CLIs, and conversations without confusing owners or sessions.
One memory layer for every agent — every entry knows who wrote it
XMemo is Yonro's hosted memory service for AI agents, with public registration at xmemo.dev. Connect an agent through documented MCP or REST clients, then review and manage your own account memories in the authenticated Memory Console.

This published image shows XMemo selected in the ChatGPT composer and contains no account memory or credentials. The Memory Console is behind sign-in; its public guide explains how to search and manage your own memories.
Start from the public registration page at xmemo.dev.
Follow the official quickstart to configure an MCP client, CLI, or supported integration.
After sign-in, use the Memory Console to search records, inspect attribution, and manage your own memory.
XMemo is open for registration at xmemo.dev and documents MCP, REST, client setup, and an authenticated Memory Console for searching and managing account-owned memories.
A common memory layer spans Copilot, Claude, Codex, Gemini, IDEs, CLIs, and conversations without confusing owners or sessions.
Every entry carries agent identity and local instance attribution, so teams know which agent wrote or used each memory.
Agents can search, recall, remember, update, forget, redact, restore, and explain memory through MCP tools and REST endpoints.
The live XMemo service runs on Azure infrastructure. Microsoft for Startups is listed as a program supporter on XMemo's public site.
Discovery endpoints provide client configuration for Codex, ChatGPT, Gemini CLI, Copilot CLI, Claude Code, Cursor, Cline, Continue, Windsurf, and generic MCP clients.
Use the hosted MCP endpoint, REST API, or the npm client: npm install -g @xmemo/client.
Discovery is read-only, tokens stay out of URLs and source control, and agents cannot run migrations, rotate tokens, or alter server configuration.
Recall feedback, eval judgments, lifecycle runs, version history, conflict resolution, forget/redact, reminders, decisions, timelines, and audit queries keep memory reviewable.
Existing agents do not need to implement memory storage and recall themselves; they connect XMemo through MCP, REST, CLI, or official client profiles.
Project facts, user corrections, decisions, and deployment state can be recalled at the next task start instead of being rediscovered.
Group memories by project and use explicit workspace boundaries where available; account-owned records remain behind sign-in.
Codex, ChatGPT, Gemini CLI, Copilot CLI, Claude Code, Cursor, Claude Desktop, Cline, Continue, Windsurf, and generic MCP clients can be configured from XMemo discovery endpoints.
Versioning, conflict detection, forget/redact, audit logs, recall feedback, and token boundaries make agent memory reviewable instead of opaque.
Create an account at xmemo.dev to use the live service. Public registration is available without an access request.
Create an XMemo account at xmemo.dev or bring a concrete agent integration to Yonro. XMemo is operated by Yonro Co., Ltd.; follow the official quickstart to connect supported AI clients.