Vertiso Memory
A portable, user-owned memory for MCP-capable agents in VS Code, enabling cross-agent recall and memory creation.
README
Vertiso Memory for VS Code
Vertiso Memory gives GitHub Copilot and other MCP-capable agents in VS Code a portable, user-owned memory that follows you between tools.
The extension registers Vertiso Memory's remote MCP server and four Agent Skills with VS Code. VS Code performs the OAuth sign-in and stores the resulting authorization. The extension does not read or retain your Vertiso credentials.
Connect
- Install the extension.
- Open Chat in VS Code and view the available MCP servers.
- Start Vertiso Memory and complete the browser sign-in when VS Code asks.
- Ask the agent to remember or recall something.
Existing manual Vertiso Memory entries in mcp.json should be removed to avoid
showing the same server twice.
What it provides
- Cross-agent memory recall and search.
- Explicit memory creation with safety controls.
- Agent Skills for checkpoints, handoffs, handoff resume, and wrap-up.
- OAuth authentication managed by VS Code.
Optional SessionStart primer
The extension does not silently write files under ~/.copilot or install a
SessionStart hook. The MCP server instructions provide the normal session
primer.
To opt into CLI-managed VS Code setup, including user-directory skill copies
and a vmem hello SessionStart hook, run:
vmem mcp install vscode
Use either the extension's remote OAuth MCP setup or the CLI-managed setup. Using both can show Vertiso Memory twice in the MCP server list.
Vertiso Memory only stores information when you or your agent explicitly calls its tools. It refuses secrets and other inappropriate memory content. See the privacy policy and documentation for details.
Support
Visit Vertiso Memory support to report a
problem or ask a question. Source and issue tracking live in the public
Vertiso/memory-vscode
repository.
This repository is a generated public mirror of Vertiso Memory's canonical distribution source. Open issues here, but do not submit pull requests or emergency source changes directly: the next mirror run replaces the repository tree. Contact support when a source change is required.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.