Cogmemai runs on your own machine — the client starts it, so there is no endpoint to ping. 638 installs a week from npm. Last commit 31 Oct 2026.
Memory for any Ai: remembers across sessions, enforces your rules before actions, reviews the work.
We read the source, 1 d ago · rules 995398eba69f
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.
return execSync(`git ${args}`, { cwd, encoding: 'utf-8', timeout: 8000, stdio: ['pipe', 'pipe', 'pipe'] }).trim();
import { readFileSync, writeFileSync, mkdirSync, existsSync, unlinkSync, readdirSync, statSync, appendFileSync, realpathSync } from 'fs';
${G('docker\\s+run\\b[^|]*--privileged\\b')}
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 mcp add cogmemai -e 'COGMEMAI_API_KEY=<COGMEMAI_API_KEY>' -- npx -y cogmemai-mcp
{
"mcpServers": {
"cogmemai": {
"command": "npx",
"args": [
"-y",
"cogmemai-mcp"
],
"env": {
"COGMEMAI_API_KEY": "<COGMEMAI_API_KEY>"
}
}
}
}
[mcp_servers.cogmemai]
command = "npx"
args = ["-y", "cogmemai-mcp"]
env = { COGMEMAI_API_KEY = "<COGMEMAI_API_KEY>" }
{
"mcpServers": {
"cogmemai": {
"command": "npx",
"args": [
"-y",
"cogmemai-mcp"
],
"env": {
"COGMEMAI_API_KEY": "<COGMEMAI_API_KEY>"
}
}
}
}
{
"servers": {
"cogmemai": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"cogmemai-mcp"
],
"env": {
"COGMEMAI_API_KEY": "<COGMEMAI_API_KEY>"
}
}
}
}
Put your own value in place of
<COGMEMAI_API_KEY> (Your CogmemAi API key from hifriendbot.com/developer/).
The author’s registry entry marks it as required.
Local memory your AI tools share: decisions, notes and corrections that carry across sessions.
Persistent memory for AI coding tools via MCP. Remembers across sessions and machines.
Cross-session, cross-device memory for your agent: remember and recall notes. No key to start.
AI session memory: the brief your AI reads before every session so no session starts cold.
Persistent memory for AI agents. Search, store, and recall across sessions.
Persistent memory for AI assistants. Store, search, and recall across sessions.
Memory for AI agent teams across tools, sessions, repositories, and teammates.
One memory for every AI you work with: your rules, notes and decisions in your own Git repo.
Answers built from our own checks of this server.