Vertiso Memory for Visual Studio Code

One memory, every agent

Decide it anywhere. Visual Studio Code already knows.

What you settle in one tool is on hand in Visual Studio Code, typed and waiting for your confirmation.

Claude Desktop 9:41 AM

You Heads up: the billing cutover moves to Oct 14. Stripe webhooks stay on v2 until then.

Claude Noted. I saved that as a decision with the v2 constraint attached, dated today.

Remembered · decision · constraint

Same room

VS Code · new session 9:42 AM

You Start the webhook migration branch.

Copilot Your memory says the cutover is Oct 14 and v2 stays live until then. I'll scaffold the v3 handler behind a flag and leave v2 untouched.

Recalled · decision · nothing re-explained

times you repeat yourself

8 types

decision, constraint, action, and more

You confirm

nothing closes itself

Install in Visual Studio Code

The same steps as the install guide, for this tool only: a live Marketplace listing where one exists, the public plugin repository, native HTTP MCP, then the local vmem bridge.

Vertiso Memory MCP URL

https://memory.vertiso.ai/mcp

The complete extension is available from Vertiso's public GitHub repository while its Marketplace listing is not yet live. A local build adds the remote MCP server and all four Agent Skills. After publication, uninstall the local 1.0.0 build before installing from the Marketplace so it owns future updates.

VS Code extension source (GitHub)

# Build-only requirements: Node.js 24 and npm
git clone https://github.com/Vertiso/memory-vscode.git
cd memory-vscode
npm ci
npm run package
# Run "Extensions: Install from VSIX..." and select:
# build/vertiso-memory-vscode.vsix

MCP-only alternative. In VS Code, run MCP: Add Server → HTTP , paste the URL, and confirm. VS Code opens your browser for OAuth. You can also put the config below in .vscode/mcp.json or your user mcp.json.

VS Code mcp.json (OAuth, MCP only)

{
  "servers": {
    "vertiso-memory": {
      "type": "http",
      "url": "https://memory.vertiso.ai/mcp"
    }
  }
}

Need a bearer token or the local vmem bridge?

Direct HTTP also accepts a bearer token stored in the MCP config:

VS Code mcp.json direct HTTP (fallback)

{
  "servers": {
    "vertiso-memory": {
      "type": "http",
      "url": "https://memory.vertiso.ai/mcp",
      "headers": {
        "Authorization": "Bearer <paste your token here>",
        "X-Agent-Source": "agent:vscode"
      }
    }
  }
}

For a CLI-managed local bridge, skills, and SessionStart primer, run vmem mcp install vscode. The bridge keeps its token in ~/.vmem. It also covers the github.com Copilot coding agent, which cannot use remote OAuth servers.

VS Code mcp.json (vmem bridge)

{
  "servers": {
    "vertiso-memory": {
      "command": "<run `which vmem` to get the absolute path>",
      "args": ["mcp", "serve", "--client", "vscode"]
    }
  }
}

Use only one setup path to avoid duplicate servers. Run MCP: List Servers → Start after changing the configuration.

Recommended: add a bootstrap instruction to your Copilot custom instructions (.github/copilot-instructions.md) so your assistant registers with Vertiso Memory at the start of every session:

Bootstrap instruction

Vertiso Memory (vmem) is my persistent memory across every tool and session.

- Call the `hello` tool at the start of every session. Treat its primer
  as authoritative context, not a suggestion.
- `recall` before planning or answering anything that may depend on
  earlier context. Look it up instead of asking me to repeat it.
- `remember` durable decisions, preferences, constraints, and project
  state the moment they land. `update_memory` rather than writing a
  near-duplicate.
- Offer a handoff before the session ends, compacts, or moves to
  another tool.

Connected? Start a new conversation and say Hello. Your assistant greets you by name and mentions what it remembers. The standing instruction and the first conversation →

API token

Only the vmem bridge and the bearer-token fallbacks need one. OAuth clients sign in during the handshake instead.

Power users: the vmem CLI

A native binary for working memory from the terminal, and a stdio-to-HTTP bridge for clients that cannot reach a remote server. It keeps your token in ~/.vmem instead of each app's config.

Install vmem

curl -fsSL https://memory.vertiso.ai/install.sh | sh

Every vmem command →

Your memory, inside Visual Studio Code.

Decide it anywhere. Visual Studio Code already knows.

Install in Visual Studio Code

Start building your memory layer.