Gmem MCP Server

by yksanjo Your server? Claim it

local only

Gmem runs on your own machine — the client starts it, so there is no endpoint to ping. 35 installs a week from npm. Last commit 10 Jul 2026.

Persistent, Solana-aware project memory for AI coding agents. Typed entities + git-aware diffs.

Installs per day peak 11 · avg 6 · +46% w/w

a month agotoday

Installs / week

npm · @yksanjo/gmem

Stars

0 open issues

10 Jul 2026

Last commit

0 releases in 90 days

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Gmem every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add gmem -- npx -y @yksanjo/gmem

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "gmem": {
      "args": [
        "-y",
        "@yksanjo/gmem"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.gmem]
command = "npx"
args = ["-y", "@yksanjo/gmem"]

.cursor/mcp.json

{
  "mcpServers": {
    "gmem": {
      "args": [
        "-y",
        "@yksanjo/gmem"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "gmem": {
      "args": [
        "-y",
        "@yksanjo/gmem"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: GMEM_DB (Override the auto-resolved memory database path. Defaults to ~/.gmem/<projectHash>/memory.db, with one db file per Solana project (project root resolved from Anchor.toml or workspace Cargo.toml).). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Gmem

same job, measured the same way

projectmind

by nodemint-dev

Persistent project memory for AI coding agents: one compact digest instead of re-reading the repo.

65 installs/wk local only

PMB AI

by oleksiijko

Local-first persistent memory for AI coding agents.

293 installs/wk local only

Gitmem

by gitmem-dev

Persistent institutional memory for AI coding agents. Memory that compounds.

113 installs/wk local only

Openfuse MCP

by openfused

Encrypted mail, shared memory, and persistent context for AI agents.

111 installs/wk local only

Omega Memory

by omega-memory

Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.

local only

Contextual

by contextual-laboratories

Persistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.

local only

robo-cortex

by robotel-limited

Git-aware memory store for AI coding agents; memories are anchored to git blob hashes.

504 installs/wk local only

Cachly Dev

by cachly-dev

Persistent memory + causal root-cause analysis for AI coding agents. 124 MCP tools. EU, GDPR.

473 installs/wk local only

Gmem — questions

Answers built from our own checks of this server.

Why is there no uptime for Gmem?

Gmem runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @yksanjo/gmem was installed 35 times last week.

How do I connect Gmem?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls @yksanjo/gmem straight from npm; nothing to host, nothing to sign up for.

How many people use Gmem?

The npm package @yksanjo/gmem was installed 35 times in the last week. Week over week that is +46%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Gmem open source?

Yes — it is published under the MIT licence, written in TypeScript and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.