mcpbeat Sign in

skillmem MCP Server

by liza-studio Your server? Claim it
local only

skillmem runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 17 Sep 2026.

Skill memory for coding agents: learn, recall, reinforce, decay. Local SQLite, no API key.

Installs / week
pypi · skillmem
4
Stars
2 open issues
17 Sep 2026
Last commit
no recent releases
Apache-2.0
License
Python

What the code does

We read the source, 19 h ago · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

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.

run in your terminal
claude mcp add skillmem -- uvx skillmem
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "skillmem": {
      "args": [
        "skillmem"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.skillmem]
command = "uvx"
args = ["skillmem"]
.cursor/mcp.json
{
  "mcpServers": {
    "skillmem": {
      "args": [
        "skillmem"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "skillmem": {
      "args": [
        "skillmem"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: SKILLMEM_DB (Path to the SQLite database file (default: the platform data directory)). The author declared them in the registry entry; get the values from the project itself.

Alternatives to skillmem

same job, measured the same way
Tdai Memory MCP
by tinhien11

Local-first MCP memory server for coding agents. No API key, no cloud. SQLite + FTS5 + sqlite-vec.

126 installs/wk local only
Myc
by aistastudio

Task queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.

2 268 installs/wk local only
Memory Kernel
by artem362

Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.

122 installs/wk local only
remem-mcp — Local-first MCP Memory + CodeGraph + Wiki
by tinhien11

Local-first memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file.

92 installs/wk local only
rmbr
by srock44

Embedded, local-first memory and retrieval for AI agents. One SQLite file, no server, no API key.

130 installs/wk local only
Leteo
by asanabrial

Persistent memory for AI coding agents: one Rust binary, one local SQLite database.

54 installs/wk local only
Palace
by ancientice

Local-first memory for coding agents — MCP server, single SQLite file, local embeddings

local only
Th Memory MCP
by worakorn-prince

Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor

449 installs/wk local only

skillmem — questions

Answers built from our own checks of this server.

Why is there no uptime for skillmem?
skillmem 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 pypi package skillmem.
How do I connect skillmem?
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 skillmem straight from pypi; nothing to host, nothing to sign up for.
Is skillmem open source?
Yes — it is published under the Apache-2.0 licence, written in Python, 4 stars on GitHub and 2 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.